Prompt-based essay writing is an effective and common way to assess students' critical thinking skills. Recent work has evaluated the impressive capabilities of Large Language Models (LLMs) on this task. However, most studies focus primarily on English. Those examining LLMs' performance in Chinese often rely on coarse-grained text quality metrics, overlooking the structural and rhetorical complexities of Chinese essays, particularly across diverse genres. We therefore propose EssayBench, a multi-genre benchmark specifically designed for Chinese essay writing, along with a fine-grained, genre-specific scoring framework that hierarchically aggregates scores to better align with human preferences. The dataset comprises 728 real-world prompts across four major genres (Argumentative, Narrative, Descriptive, and Expository), and includes both Open-Ended and Constrained types. Our evaluation protocol is validated through a comprehensive human agreement study. The results show that our protocol aligns well with human judgments, achieving a highest Spearman's correlation of 0.816 and outperforming coarse-grained evaluation methods by an average of 8.6\%. Finally, we benchmark 15 large LLMs, analyzing their strengths and limitations across genres and instruction types. We believe EssayBench offers a more reliable framework for evaluating Chinese essay generation and provides valuable insights for improving LLMs in this domain.

Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabilities. However, existing approaches primarily focus on data synthesis for fine-tuning LLMs to invoke tools effectively, largely ignoring how to fully stimulate the potential of the model. In this paper, we propose ToolACE-R, a novel framework that includes both model-aware iterative training and adaptive refinement for tool learning. ToolACE-R features a model-aware iterative training procedure that progressively adjust training samples based on the model’s evolving capabilities to maximize its potential. Additionally, it incorporates self-refinement training corpus which emphasizes LLM's ability to iteratively refine their tool calls, optimizing performance without requiring external feedback. Furthermore, we introduce adaptive self-refinement for efficient test-time scaling, where the trained model can autonomously determine when to stop the process based on iterative self-refinement. We conduct extensive experiments across several benchmark datasets, showing that ToolACE-R achieves competitive performance compared to advanced LLMs. The performance can be further improved efficiently through adaptive self-refinement. These results highlight the effectiveness and generalizability of ToolACE-R, offering a promising direction for more efficient and scalable tool learning.

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as process reward models (PRMs) or self-consistency operate as opaque boxes and do not provide checkable evidence for their judgments, possibly limiting their effectiveness. To address this issue, we draw inspiration from the idea that “the gold standard for supporting a mathematical claim is to provide a proof”. We propose a retrospective, step-aware formal verification framework Safe. Rather than assigning arbitrary scores, we strive to articulate mathematical claims in formal mathematical language Lean 4 at each reasoning step and provide formal proofs to identify hallucinations. We evaluate our framework Safe across multiple language models and various mathematical datasets, demonstrating a significant performance improvement while offering interpretable and verifiable evidence. We also propose FormalStep as a benchmark for step correctness theorem proving with 30,809 formal statements. To the best of our knowledge, our work represents the first endeavor to utilize formal mathematical language Lean 4 for verifying content generated by LLMs, aligning with the reason why formal mathematical languages were created in the first place: to provide a robust foundation for hallucination-prone human-written proofs.

With the impressive reasoning and text generation capabilities of large language models (LLMs), methods leveraging multiple LLMs to debate each other have garnered increasing attention. However, existing debate-based approaches remain limited in effectiveness in structured and detailed domains represented by code generation due to several reasons: 1) Reliance on different instances of the same LLM for debate, neglecting the potential benefits of integrating diverse models with varied internal knowledge for more comprehensive code generation, 2) under-utilization of test cases, and 3) reliance on third-party LLM moderators for result consolidation and decision-making, probably introducing hallucinations and judgment errors. To address these challenges, we propose DebateCoder to collect intelligence of LLMs via test case-driven debate for code generation. In DebateCoder, test cases serve as a medium for models to analyze code and identify bugs, while opposing models generate test cases to challenge each other’s code during the debate process. These test cases, along with their execution results, are elaborately leveraged to refine and enhance the code through a novel contrastive analysis process. Furthermore, DebateCoder leverages test case outcomes to assess code quality and determine convergence criteria. Unlike previous approaches, DebateCoder emphasizes the collaborative improvement of both models through competitive debate and interactive analysis. Abundant experimental results on two datasets demonstrate the effectiveness of DebateCoder.

Xiangyang Li, Kuicai Dong, Yi Quan Lee, Wei Xia, Hao Zhang, Xinyi Dai, Yasheng Wang, Ruiming Tang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Wenjun Li, Dexun Li, Kuicai Dong, Cong Zhang, Hao Zhang, Weiwen Liu, Yasheng Wang, Ruiming Tang, Yong Liu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Qiyuan Zhang, Yufei Wang, Yuxin Jiang, Liangyou Li, Chuhan Wu, Yasheng Wang, Xin Jiang, Lifeng Shang, Ruiming Tang, Fuyuan Lyu, Chen Ma. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Minda Hu, Qiyuan Zhang, Yufei Wang, Bowei He, Hongru Wang, Jingyan Zhou, Liangyou Li, Yasheng Wang, Chen Ma, Irwin King. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Qingyao Li, Wei Xia, Xinyi Dai, Kounianhua Du, Weiwen Liu, Yasheng Wang, Ruiming Tang, Yong Yu, Weinan Zhang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Yufei Wang, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Weiming Zhang, Qingyao Li, Xinyi Dai, Jizheng Chen, Kounianhua Du, Weiwen Liu, Yasheng Wang, Ruiming Tang, Yong Yu, Weinan Zhang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Smartphone agents are increasingly important for helping users control devices efficiently, with (Multimodal) Large Language Model (MLLM)-based approaches emerging as key contenders. Fairly comparing these agents is essential but challenging, requiring a varied task scope, the integration of agents with different implementations, and a generalisable evaluation pipeline to assess their strengths and weaknesses. In this paper, we present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents in an interactive environment that simulates real-world conditions. SPA-Bench offers three key contributions: (1) A diverse set of tasks covering system and third-party apps in both English and Chinese, focusing on features commonly used in daily routines; (2) A plug-and-play framework enabling real-time agent interaction with Android devices, integrating over ten agents with the flexibility to add more; (3) A novel evaluation pipeline that automatically assesses agent performance across multiple dimensions, encompassing seven metrics related to task completion and resource consumption. Our extensive experiments across tasks and agents reveal challenges like interpreting mobile user interfaces, action grounding, memory retention, and execution costs. We propose future research directions to ease these difficulties, moving closer to real-world smartphone agent applications.

Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and APIs may become outdated over time, preventing LLMs from correctly invoking tools. Existing research primarily focuses on static environments and overlooks this issue, limiting the adaptability of LLMs in real-world applications. In this paper, we propose ToolEVO, a novel framework designed to enhance the adaptive and reflective capabilities of LLMs against tool variability. By leveraging Monte Carlo Tree Search, ToolEVO facilitates active exploration and interaction of LLMs within dynamic environments, allowing for autonomous self-reflection and self-updating of tool usage based on environmental feedback. Additionally, we introduce ToolQA-D, a benchmark specifically designed to evaluate the impact of tool variability. Extensive experiments demonstrate the effectiveness and stability of our approach, highlighting the importance of adaptability to tool variability for effective tool learning.

Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired behaviors using pairwise preference data. However, the generation of the winning response and the losing response within pairwise data are typically isolated, leading to weak correlations between them as well as suboptimal alignment performance. To address this issue, we propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC. Firstly, we increase the consistency and informativeness of the pairwise preference signals through targeted modifications, synthesizing a pseudo-winning response by improving the losing response with the winning response as a reference. Secondly, we identify that DPO alone is insufficient to model these correlations and capture nuanced variations. Therefore, we propose learning token-level correlations by dynamically leveraging the policy model's confidence during training. Comprehensive experiments on QA, math, and instruction-following tasks demonstrate the effectiveness of our approach, significantly surpassing competitive baselines, including DPO. Additionally, our in-depth quantitative analysis reveals the reasons behind our method's superior performance over DPO and showcases its versatility to other DPO variants.

Function calling significantly extends the application boundary of large language models (LLMs), where high-quality and diverse training data is critical for unlocking this capability. However, collecting and annotating real function-calling data is challenging, while synthetic data from existing pipelines often lack coverage and accuracy. In this paper, we present ToolACE, an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data, specifically tailored to the capabilities of LLMs. ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, under the guidance of a complexity evaluator. To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks. We demonstrate that models trained on our synthesized data---even with only 8B parameters---achieve state-of-the-art performance, comparable to the latest GPT-4 models. Our model and a subset of the data are publicly available at https://huggingface.co/Team-ACE.

Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In this paper, we tackle the challenge of developing proactive agents capable of anticipating and initiating tasks without explicit human instructions. We propose a novel data-driven approach for this problem. Firstly, we collect real-world human activities to generate proactive task predictions. These predictions are then labeled by human annotators as either accepted or rejected. The labeled data is used to train a reward model that simulates human judgment and serves as an automatic evaluator of the proactiveness of LLM agents. Building on this, we develop a comprehensive data generation pipeline to create a diverse dataset, ProactiveBench, containing 6,790 events. Finally, we demonstrate that fine-tuning models with the proposed ProactiveBench can significantly elicit the proactiveness of LLM agents. Experimental results show that our fine-tuned model achieves an F1-Score of 66.47% in proactively offering assistance, outperforming all open-source and close-source models. These results highlight the potential of our method in creating more proactive and effective agent systems, paving the way for future advancements in human-agent collaboration.

With significant efforts in recent studies, LLM-as-a-Judge has become a cost-effective alternative to human evaluation for assessing text generation quality in a wide range of tasks. However, there still remains a reliability gap between LLM-as-a-Judge and human evaluation. One important reason is the lack of guided oracles in the evaluation process. Motivated by the role of reference pervasively used in classic text evaluation, we introduce RevisEval, a novel text generation evaluation paradigm via the response-adapted references. RevisEval is driven by the key observation that an ideal reference should maintain the necessary relevance to the response to be evaluated. Specifically, RevisEval leverages the text revision capabilities of large language models (LLMs) to adaptively revise the response, then treat the revised text as the reference (response-adapted reference) for the subsequent evaluation. Extensive experiments demonstrate that RevisEval outperforms traditional reference-free and reference-based evaluation paradigms that use LLM-as-a-Judge across NLG tasks and open-ended instruction-following tasks. More importantly, our response-adapted references can further boost the classical text metrics, e.g., BLEU and BERTScore, compared to traditional references and even rival the LLM-as-a-Judge. A detailed analysis is also conducted to confirm RevisEval's effectiveness in bias reduction, the impact of inference cost, and reference relevance.

Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tuning (PEFT) method, offers an efficient solution by optimizing only low-rank matrices. Despite recent progress in improving LoRA’s performance, the relationship between the LoRA optimization space and the full parameter space is often overlooked. A solution that appears flat in the loss landscape of the LoRA space may still exhibit sharp directions in the full parameter space, potentially compromising generalization. We introduce Flat-LoRA, which aims to identify a low-rank adaptation situated in a flat region of the full parameter space. Instead of adopting the well-established sharpness-aware minimization approach, which incurs significant computation and memory overheads, we employ a Bayesian expectation loss objective to preserve training efficiency. Further, we design a refined strategy for generating random perturbations to enhance performance and carefully manage memory overhead using random seeds. Experiments across diverse tasks—including mathematical reasoning, coding abilities, dialogue generation, instruction following, and text-to-image generation—demonstrate that Flat-LoRA improves both in-domain and out-of-domain generalization. Code is available at https://github.com/nblt/Flat-LoRA.

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current document retrieval-augmented generation (DocRAG) methods remain limited by their text-centric approaches, frequently missing critical visual information. The field also lacks robust benchmarks for assessing multimodal evidence selection and integration. We introduce MMDocRAG, a comprehensive benchmark featuring 4,055 expert-annotated QA pairs with multi-page, cross-modal evidence chains. Our framework introduces innovative metrics for evaluating multimodal quote selection and enables answers that interleave text with relevant visual elements. Through large-scale experiments with 60 VLM/LLM models and 14 retrieval systems, we identify persistent challenges in multimodal evidence retrieval, selection, and integration. Key findings reveal that advanced proprietary LVMs show superior performance than open-sourced alternatives. Also, they show moderate advantages using multimodal inputs over text-only inputs, while open-source alternatives show significant performance degradation. Notably, fine-tuned LLMs achieve substantial improvements when using detailed image descriptions. MMDocRAG establishes a rigorous testing ground and provides actionable insights for developing more robust multimodal DocVQA systems.

Recent advancements in Long Chain-of-Thought (CoT) reasoning models have improved performance on complex tasks, but they suffer from overthinking, which generates redundant reasoning steps, especially for simple questions. This paper revisits the reasoning patterns of Long and Short CoT models, observing that the Short CoT patterns offer concise reasoning efficiently, while the Long CoT patterns excel in challenging scenarios where the Short CoT patterns struggle. To enable models to leverage both patterns, we propose Question-Free Fine-Tuning (QFFT), a fine-tuning approach that removes the input question during training and learns exclusively from Long CoT responses. This approach enables the model to adaptively employ both reasoning patterns: it prioritizes the Short CoT patterns and activates the Long CoT patterns only when necessary. Experiments on various mathematical datasets demonstrate that QFFT reduces average response length by more than 50\%, while achieving performance comparable to Supervised Fine-Tuning (SFT). Additionally, QFFT exhibits superior performance compared to SFT in noisy, out-of-domain, and low-resource scenarios.

Information seeking demands iterative evidence gathering and reflective reasoning, yet large language models (LLMs) still struggle with it in open-web question answering. Existing prompting and supervised fine-tuning (SFT) methods remain fixed by prompt rules or training corpora, and are usually benchmarked only on well-structured wiki sources, limiting real-world adaptability. We introduce $\textbf{WebPuzzle}$, a 24k-sample training and 275-sample test benchmark that evaluates information seeking on the live internet, across both wiki and open-domain queries. Leveraging 7k WebPuzzle instances, we develop $\textbf{DeepDiver}$, a reinforcement-learning (RL) framework that cultivates $\textbf{Search Intensity Scaling (SIS)}$—an emergent ability to escalate search frequency and depth instead of settling on overconfident, under-evidenced answers. With SIS, Qwen2.5-7B-Instruct and Pangu-7B-Reasoner attain performance on real-web tasks comparable to the 671B-parameter DeepSeek-R1. We detail DeepDiver’s curriculum from cold-start SFT to a well designed RL procedure, and show that its seeking policy generalized from closed-ended queries to open-ended generation such as long-form writing. Our results advance adaptive information seeking in LLMs and provide a rigorous benchmark for future work.

As one of the state-of-the-art parameter-efficient fine-tuning~(PEFT) methods, Low-Rank Adaptation (LoRA) enables model optimization with reduced computational cost through trainable low-rank matrix. However, the low-rank nature makes it prone to produce a decrease in the representation ability, leading to suboptimal performance. In order to break this limitation, we propose RidgeLoRA, a lightweight architecture like LoRA that incorporates novel architecture and matrix ridge enhanced full-rank approximation, to match the performance of full-rank training, while eliminating the need for high memory and a large number of parameters to restore the rank of matrices. We provide a rigorous mathematical derivation to prove that RidgeLoRA has a better upper bound on the representations than vanilla LoRA. Furthermore, extensive experiments across multiple domains demonstrate that RidgeLoRA achieves better performance than other LoRA variants, and can even match or surpass full-rank training.

Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Knowledge Tracing (KT) aims to determine whether students will respond correctly to the next question, which is a crucial task in intelligent tutoring systems (ITS). In educational KT scenarios, transductive ID-based methods often face severe data sparsity and cold start problems, where interactions between individual students and questions are sparse, and new questions and concepts consistently arrive in the database. In addition, existing KT models only implicitly consider the correlation between concepts and questions, lacking direct modeling of the more complex relationships in the heterogeneous graph of concepts and questions. In this paper, we propose a Structure-aware INductive Knowledge Tracing model with large language model (dubbed SINKT), which, for the first time, introduces large language models (LLMs) and realizes inductive knowledge tracing. Firstly, SINKT utilizes LLMs to introduce structural relationships between concepts and constructs a hetero- geneous graph for concepts and questions. Secondly, by encoding concepts and questions with LLMs, SINKT incorporates semantic information to aid prediction. Finally, SINKT predicts the student's response to the target question by interacting with the student's knowledge state and the question representation. Experiments on four real-world datasets demonstrate that SINKT achieves state-of-the-art performance among 12 existing transductive KT models. Additionally, we explore the performance of SINKT on the inductive KT task and provide insights into various modules.

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales is relatively scarce due to the high annotation cost. To address this issue, we propose Self-motivated Learning framework. The framework motivates the model itself to automatically generate rationales on existing datasets. Based on the inherent rank from correctness across multiple rationales, the model learns to generate better rationales, leading to higher reasoning capability. Specifically, we train a reward model with the rank to evaluate the quality of rationales, and improve the performance of reasoning through reinforcement learning. Experiment results of Llama2 7B on multiple reasoning datasets show that our method significantly improves the reasoning ability of models, even outperforming InstructGPT in some datasets.

Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively engage with the user and successfully complete the dialogue. However, most previous work trained independent retrievers for each specific resource, resulting in sub-optimal performance and low efficiency. Thus, we propose a multi-task framework function as a universal retriever for three dominant retrieval tasks during the conversation: persona selection, knowledge selection, and response selection. To this end, we design a dual-encoder architecture consisting of a context-adaptive dialogue encoder and a candidate encoder, aiming to attention to the relevant context from the long dialogue and retrieve suitable candidates by simply a dot product. Furthermore, we introduce two loss constraints to capture the subtle relationship between dialogue context and different candidates by regarding historically selected candidates as hard negatives. Extensive experiments and analysis establish state-of-the-art retrieval quality both within and outside its training domain, revealing the promising potential and generalization capability of our model to serve as a universal retriever for different candidate selection tasks simultaneously.

Incorporating external knowledge into the response generation process is essential to building more helpful and reliable dialog agents. However, collecting knowledge-grounded conversations is often costly, calling for a better pre-trained model for grounded dialog generation that generalizes well w.r.t. different types of knowledge. In this work, we propose KPT (Keyword-guided Pre-Training), a novel self-supervised pre-training method for grounded dialog generation without relying on extra knowledge annotation. Specifically, we use a pre-trained language model to extract the most uncertain tokens in the dialog as keywords. With these keywords, we construct two kinds of knowledge and pre-train a knowledge-grounded response generation model, aiming at handling two different scenarios: (1) the knowledge should be faithfully grounded; (2) it can be selectively used. For the former, the grounding knowledge consists of keywords extracted from the response. For the latter, the grounding knowledge is additionally augmented with keywords extracted from other utterances in the same dialog. Since the knowledge is extracted from the dialog itself, KPT can be easily performed on a large volume and variety of dialogue data. We considered three data sources (open-domain, task-oriented, conversational QA) with a total of 2.5M dialogues. We conduct extensive experiments on various few-shot knowledge-grounded generation tasks, including grounding on dialog acts, knowledge graphs, persona descriptions, and Wikipedia passages. Our comprehensive experiments and analyses demonstrate that KPT consistently outperforms state-of-the-art methods on these tasks with diverse grounding knowledge.

Hao Sun, Zhexin Zhang, Fei Mi, Yasheng Wang, Wei Liu, Jianwei Cui, Bin Wang, Qun Liu, Minlie Huang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Training grounded response generation models often requires a large collection of grounded dialogues.However, it is costly to build such dialogues.In this paper, we present a synthetic data generation framework (SynDG) for grounded dialogues.The generation process utilizes large pre-trained language models and freely available knowledge data (e.g., Wikipedia pages, persona profiles, etc.).The key idea of designing SynDG is to consider dialogue flow and coherence in the generation process.Specifically, given knowledge data, we first heuristically determine a dialogue flow, which is a series of knowledge pieces.Then, we employ T5 to incrementally turn the dialogue flow into a dialogue.To ensure coherence of both the dialogue flow and the synthetic dialogue, we design a two-level filtering strategy, at the flow-level and the utterance-level respectively.Experiments on two public benchmarks show that the synthetic grounded dialogue data produced by our framework is able to significantly boost model performance in both full training data and low-resource scenarios.

Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability.Specifically, most of the wellperformed metrics are required to train on evaluation datasets of specific NLG tasks and evaluation dimensions, which may cause over-fitting to task-specific datasets.Furthermore, existing metrics only provide an evaluation score for each dimension without revealing the evidence to interpret how this score is obtained.To deal with these challenges, we propose a simple yet effective metric called DecompEval.This metric formulates NLG evaluation as an instruction-style question answering task and utilizes instruction-tuned pre-trained language models (PLMs) without training on evaluation datasets, aiming to enhance the generalization ability.To make the evaluation process more interpretable, we decompose our devised instruction-style question about the quality of generated texts into the subquestions that measure the quality of each sentence.The subquestions with their answers generated by PLMs are then recomposed as evidence to obtain the evaluation result.Experimental results show that DecompEval achieves state-of-the-art performance in untrained metrics for evaluating text summarization and dialogue generation, which also exhibits strong dimension-level / task-level generalization ability and interpretability 1 .

Yajiao Liu, Xin Jiang, Yichun Yin, Yasheng Wang, Fei Mi, Qun Liu, Xiang Wan, Benyou Wang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Rui Wang, Jianzhu Bao, Fei Mi, Yi Chen, Hongru Wang, Yasheng Wang, Yitong Li, Lifeng Shang, Kam-Fai Wong, Ruifeng Xu. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Recently, semantic parsing using hierarchical representations for dialog systems has captured substantial attention. Task-Oriented Parse (TOP), a tree representation with intents and slots as labels of nested tree nodes, has been proposed for parsing user utterances. Previous TOP parsing methods are limited on leveraging lexicon resources, which are often used to guide the real dialog system. To mitigate this issue, we first propose a novel span-splitting representation for span-based parser that outperforms existing methods. Then we present a novel lexicon-injected semantic parser, which collects slot labels of tree representation as a lexicon, and injects lexical features to the span representation of parser. An additional slot disambiguation technique is involved to remove inappropriate span match occurrences from the lexicon. Experiments show that our best parser produces a new state-of-the-art result (87.62%) on the TOP dataset, and also confirm the effectiveness of our proposed lexicon-injected parser and slot disambiguation model.

Dialogue history and response in open-domain dialogue are loosely coupled. Generating informative responses solely based on the original dialogue history is not easy, as dialogue history may not contain enough information or it may contain irrelevant noises. Intuitively, if a generation model can foresee possible dialogue future, or obtain real useful histories, it could generate more informative responses. In this paper, we propose a novel lightweight dialogue generation framework named few-shot history-future prompt that utilizes useful histories and simulated futures to help generate informative responses, without the need for fine-tuning or adding extra parameters. To obtain useful histories, we retrieve and combine relevant utterances from noisy multi- turn histories. Then we adopt a retrieval-generation hybrid approach to obtain diversified simulated futures. Such that our model could learn to condition on history combinations and simulated futures via few-shot learning. Experiments over publicly available datasets demonstrate that our method can help models generate better responses.

Multimodal abstractive summarization for videos (MAS) requires generating a concise textual summary to describe the highlights of a video according to multimodal resources, in our case, the video content and its transcript. Inspired by the success of the large-scale generative pre-trained language model (GPLM) in generating high-quality textual content (e.g., summary), recent MAS methods have proposed to adapt the GPLM to this task by equipping it with the visual information, which is often obtained through a general-purpose visual feature extractor. However, the generally extracted visual features may overlook some summary-worthy visual information, which impedes model performance. In this work, we propose a novel approach to learning the summary-worthy visual representation that facilitates abstractive summarization. Our method exploits the summary-worthy information from both the cross-modal transcript data and the knowledge that distills from the pseudo summary. Extensive experiments on three public multimodal datasets show that our method outperforms all competing baselines. Furthermore, with the advantages of summary-worthy visual information, our model can have a significant improvement on small datasets or even datasets with limited training data.

Abstract Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system where additional linguistic information exists below the character level, i.e., at the sub-character level. To utilize such information, we propose sub-character (SubChar for short) tokenization. Specifically, we first encode the input text by converting each Chinese character into a short sequence based on its glyph or pronunciation, and then construct the vocabulary based on the encoded text with sub-word segmentation. Experimental results show that SubChar tokenizers have two main advantages over existing tokenizers: 1) They can tokenize inputs into much shorter sequences, thus improving the computational efficiency. 2) Pronunciation-based SubChar tokenizers can encode Chinese homophones into the same transliteration sequences and produce the same tokenization output, hence being robust to homophone typos. At the same time, models trained with SubChar tokenizers perform competitively on downstream tasks. We release our code and models at https://github.com/thunlp/SubCharTokenization to facilitate future work.

As the labeling cost for different modules in task-oriented dialog (ToD) systems is high, a major challenge is to learn different tasks with the least amount of labeled data. Recently, pre-trained language models (PLMs) have shown promising results for few-shot learning in ToD. To better utilize the power of PLMs, this paper proposes Comprehensive Instruction (CINS) that exploits PLMs with extra task-specific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD, ie. intent classification, dialog state tracking, and natural language generation. A sequence-to-sequence model (T5) is adopted to solve these three tasks in a unified framework. Extensive experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data. Empirical results demonstrate that the proposed CINS approach consistently improves techniques that finetune PLMs with raw input or short prompt.

With the rapid increase of multimedia data, a large body of literature has emerged to work on multimodal summarization, the majority of which target at refining salient information from textual and image modalities to output a pictorial summary with the most relevant images. Existing methods mostly focus on either extractive or abstractive summarization and rely on the presence and quality of image captions to build image references. We are the first to propose a Unified framework for Multimodal Summarization grounding on BART, UniMS, that integrates extractive and abstractive objectives, as well as selecting the image output. Specially, we adopt knowledge distillation from a vision-language pretrained model to improve image selection, which avoids any requirement on the existence and quality of image captions. Besides, we introduce a visual guided decoder to better integrate textual and visual modalities in guiding abstractive text generation. Results show that our best model achieves a new state-of-the-art result on a large-scale benchmark dataset. The newly involved extractive objective as well as the knowledge distillation technique are proven to bring a noticeable improvement to the multimodal summarization task.

Real human conversation data are complicated, heterogeneous, and noisy, from which building open-domain dialogue systems remains a challenging task. In fact, such dialogue data still contains a wealth of information and knowledge, however, they are not fully explored. In this paper, we show existing open-domain dialogue generation methods that memorize context-response paired data with autoregressive or encode-decode language models underutilize the training data. Different from current approaches, using external knowledge, we explore a retrieval-generation training framework that can take advantage of the heterogeneous and noisy training data by considering them as “evidence”. In particular, we use BERTScore for retrieval, which gives better qualities of the evidence and generation. Experiments over publicly available datasets demonstrate that our method can help models generate better responses, even such training data are usually impressed as low-quality data. Such performance gain is comparable with those improved by enlarging the training set, even better. We also found that the model performance has a positive correlation with the relevance of the retrieved evidence. Moreover, our method performed well on zero-shot experiments, which indicates that our method can be more robust to real-world data.

Argument generation is an important but challenging task in computational argumentation.Existing studies have mainly focused on generating individual short arguments, while research on generating long and coherent argumentative essays is still under-explored.In this paper, we propose a new task, Argumentative Essay Generation (AEG).Given a writing prompt, the goal of AEG is to automatically generate an argumentative essay with strong persuasiveness.We construct a large-scale dataset, ArgEssay, for this new task and establish a strong model based on a dual-decoder Transformer architecture.Our proposed model contains two decoders, a planning decoder (PD) and a writing decoder (WD), where PD is used to generate a sequence for essay content planning and WD incorporates the planning information to write an essay.Further, we pre-train this model on a large news dataset to enhance the plan-and-write paradigm.Automatic and human evaluation results show that our model can generate more coherent and persuasive essays with higher diversity and less repetition compared to several baselines.1

Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Phillippe Langlais. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

Existing pre-training methods for extractive Question Answering (QA) generate cloze-like queries different from natural questions in syntax structure, which could overfit pre-trained models to simple keyword matching.In order to address this problem, we propose a novel Momentum Contrastive pRe-training fOr queStion anSwering (MCROSS) method for extractive QA.Specifically, MCROSS introduces a momentum contrastive learning framework to align the answer probability between cloze-like and natural query-passage sample pairs.Hence, the pre-trained models can better transfer the knowledge learned in cloze-like samples to answering natural questions.Experimental results on three benchmarking QA datasets show that our method achieves noticeable improvement compared with all baselines in both supervised and zero-shot scenarios.

Mispronunciation detection and diagnosis (MDD) is a popular research focus in computer-aided pronunciation training (CAPT) systems.End-to-end (e2e) approaches are becoming dominant in MDD.However an e2e MDD model usually requires entire speech utterances as input context, which leads to significant time latency especially for long paragraphs.We propose a streaming e2e MDD model called CoCA-MDD.We utilize conv-transformer structure to encode input speech in a streaming manner.A coupled cross-attention (CoCA) mechanism is proposed to integrate frame-level acoustic features with encoded reference linguistic features.CoCA also enables our model to perform mispronunciation classification with whole utterances.The proposed model allows system fusion between the streaming output and mispronunciation classification output for further performance enhancement.We evaluate CoCA-MDD on publicly available corpora.CoCA-MDD achieves F1 scores of 57.03% and 60.78% for streaming and fusion modes respectively on L2-ARCTIC.For phone-level pronunciation scoring, CoCA-MDD achieves 0.58 Pearson correlation coefficient (PCC) value on SpeechOcean762.

Adapting large pre-trained models (PTMs) through fine-tuning imposes prohibitive computational and storage burdens. Recent studies of delta tuning (DT), i.e., parameter-efficient tuning, find that only optimizing a small portion of parameters conditioned on PTMs could yield on-par performance compared to conventional fine-tuning. Generally, DT methods exquisitely design delta modules (DT modules) which could be applied to arbitrary fine-grained positions inside PTMs. However, the effectiveness of these fine-grained positions largely relies on sophisticated manual designation, thereby usually producing sub-optimal results. In contrast to the manual designation, we explore constructing DT modules in an automatic manner. We automatically \textbf{S}earch for the \textbf{S}parse \textbf{S}tructure of \textbf{Delta} Tuning (S$^3$Delta). Based on a unified framework of various DT methods, S$^3$Delta conducts the differentiable DT structure search through bi-level optimization and proposes shifted global sigmoid method to explicitly control the number of trainable parameters. Extensive experiments show that S$^3$Delta surpasses manual and random structures with less trainable parameters. The searched structures preserve more than 99\% fine-tuning performance with 0.01\% trainable parameters. Moreover, the advantage of S$^3$Delta is amplified with extremely low trainable parameters budgets (0.0009\%$\sim$0.01\%). The searched structures are transferable and explainable, providing suggestions and guidance for the future design of DT methods. Our codes are publicly available at \url{https://github.com/thunlp/S3Delta}.

Source code summarization aims at generating concise and clear natural language descriptions for programming languages. Well-written code summaries are beneficial for programmers to participate in the software development and maintenance process. To learn the semantic representations of source code, recent efforts focus on incorporating the syntax structure of code into neural networks such as Transformer. Such Transformer-based approaches can better capture the long-range dependencies than other neural networks including Recurrent Neural Networks (RNNs), however, most of them do not consider the structural relative correlations between tokens, e.g., relative positions in Abstract Syntax Trees (ASTs), which is beneficial for code semantics learning. To model the structural dependency, we propose a StruCtural RelatIve Position guided Transformer, named SCRIPT. SCRIPT first obtains the structural relative positions between tokens via parsing the ASTs of source code, and then passes them into two types of Transformer encoders. One Transformer directly adjusts the input according to the structural relative distance; and the other Transformer encodes the structural relative positions during computing the self-attention scores. Finally, we stack these two types of Transformer encoders to learn representations of source code. Experimental results show that the proposed SCRIPT outperforms the state-of-the-art methods by at least 1.6%, 1.4% and 2.8% with respect to BLEU, ROUGE-L and METEOR on benchmark datasets, respectively. We further show that how the proposed SCRIPT captures the structural relative dependencies.

Fanchao Qi, Mukai Li, Yangyi Chen, Zhengyan Zhang, Zhiyuan Liu, Yasheng Wang, Maosong Sun. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

A reverse dictionary takes the description of a target word as input and outputs the target word together with other words that match the description. Existing reverse dictionary methods cannot deal with highly variable input queries and low-frequency target words successfully. Inspired by the description-to-word inference process of humans, we propose the multi-channel reverse dictionary model, which can mitigate the two problems simultaneously. Our model comprises a sentence encoder and multiple predictors. The predictors are expected to identify different characteristics of the target word from the input query. We evaluate our model on English and Chinese datasets including both dictionary definitions and human-written descriptions. Experimental results show that our model achieves the state-of-the-art performance, and even outperforms the most popular commercial reverse dictionary system on the human-written description dataset. We also conduct quantitative analyses and a case study to demonstrate the effectiveness and robustness of our model. All the code and data of this work can be obtained on https://github.com/thunlp/MultiRD.

Sememes, the minimum semantic units of human languages, have been successfully utilized in various natural language processing applications. However, most existing studies exploit sememes in specific tasks and few efforts are made to utilize sememes more fundamentally. In this paper, we propose to incorporate sememes into recurrent neural networks (RNNs) to improve their sequence modeling ability, which is beneficial to all kinds of downstream tasks. We design three different sememe incorporation methods and employ them in typical RNNs including LSTM, GRU and their bidirectional variants. In evaluation, we use several benchmark datasets involving PTB and WikiText-2 for language modeling, SNLI for natural language inference and another two datasets for sentiment analysis and paraphrase detection. Experimental results show evident and consistent improvement of our sememe-incorporated models compared with vanilla RNNs, which proves the effectiveness of our sememe incorporation methods. Moreover, we find the sememe-incorporated models have higher robustness and outperform adversarial training in defending adversarial attack. All the code and data of this work can be obtained at https://github.com/thunlp/SememeRNN.

Although many sentiment lexicons in different languages exist, most are not comprehensive.In a recent sentiment analysis application, we used a large Chinese sentiment lexicon and found that it missed a large number of sentiment words used in social media.This prompted us to make a new attempt to study sentiment lexicon expansion.This paper first formulates the problem as a PU learning problem.It then proposes a new PU learning method suitable for the problem based on a neural network.The results are further enhanced with a new dictionary lookup technique and a novel polarity classification algorithm.Experimental results show that the proposed approach greatly outperforms baseline methods.