Critical thinking is essential for building robust AI systems, preventing them from blindly accepting flawed data or biased reasoning. However, prior work has primarily focused on passive critical thinking, where models simply reject problematic queries without taking constructive steps to address user requests. In this work, we introduce proactive critical thinking, a paradigm where models actively seek missing or clarifying information from users to resolve their queries better. To evaluate this capability, we present GSM-MC and GSM-MCE, two novel benchmarks based on GSM8K for assessing mathematical reasoning under incomplete or misleading conditions. Experiments on Qwen3 and Llama series models show that, while these models excel in traditional reasoning tasks, they struggle with proactive critical thinking, especially smaller ones. However, we demonstrate that reinforcement learning (RL) can significantly improve this ability. By incorporating heuristic information into the reward function, we achieve substantial gains, boosting the Qwen3-1.7B's accuracy from 0.15% to 73.98% on GSM-MC. We hope this work advances models that collaborate more effectively with users in problem-solving through proactive critical thinking.

Weitao Li, Boran Xiang, Xiaolong Wang, Jingyi Ren, Ante Wang, Zhinan Gou, Weizhi Ma, Yang Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhanyu Liu, Qingguo Hu, Ante Wang, Chenqing Liu, Zhishang Xiang, Hui Li, Delai Qiu, Jinsong Su. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Jingyi Ren, Ante Wang, Yunghwei Lai, Xiaolong Wang, Linlu Gong, Weitao Li, Weizhi Ma, Yang Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources of greedy decoding due to wasteful search strategies, making them difficult to be deployed in practical applications. This study introduces a novel guided tree search algorithm with a goal-directed heuristic function and node-level exploration budget (maximum number of children) calculation to tackle this issue. By considering the search progress towards the final answer (history) and the guidance from a value network (future) trained without any step-wise annotations, our algorithm iteratively selects the most promising tree node before expanding it within the boundaries of the allocated computational budget. Experiments conducted on the GSM8K, TabMWP, and MATH datasets demonstrate that our method not only offers competitive performance but also enjoys significantly lower computational costs compared to baseline methods.

Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increased computational resources. In this work, we identify two key challenges contributing to this inefficiency: \textit{over-exploration} due to redundant states with semantically equivalent content, and \textit{under-exploration} caused by high variance in verifier scoring leading to frequent trajectory switching. To address these issues, we propose FETCH – an e{\bf f}fici{\bf e}nt {\bf t}ree sear{\bf ch} framework, which is a flexible, plug-and-play system compatible with various tree search algorithms.Our framework mitigates over-exploration by merging semantically similar states using agglomerative clustering of text embeddings obtained from a fine-tuned SimCSE model. To tackle under-exploration, we enhance verifiers by incorporating temporal difference learning with adjusted \lambda-returns during training to reduce variance, and employing a verifier ensemble to aggregate scores during inference. Experiments on GSM8K, GSM-Plus, and MATH datasets demonstrate that our methods significantly improve reasoning accuracy and computational efficiency across four different tree search algorithms, paving the way for more practical applications of LLM-based reasoning. The code is available at https://github.com/DeepLearnXMU/Fetch.

Misinformation spans various domains, but detection methods trained on specific domains often perform poorly when applied to others.With the rapid development of Large Language Models (LLMs), researchers have begun to utilize LLMs for cross-domain misinformation detection.However, existing LLM-based methods often fail to adequately analyze news in the target domain, limiting their detection capabilities.More importantly, these methods typically rely on manually designed decision rules, which are limited by domain knowledge and expert experience, thus limiting the generalizability of decision rules to different domains.To address these issues, we propose a Multi-Agent Framework for cross-domain misinformation detection with Automated Decision Rule Optimization (MARO).Under this framework, we first employs multiple expert agents to analyze target-domain news.Subsequently, we introduce a question-reflection mechanism that guides expert agents to facilitate higher-quality analysis.Furthermore, we propose a decision rule optimization approach based on carefully designed cross-domain validation tasks to iteratively enhance decision rule effectiveness across domains.Experimental results and analysis on commonly used datasets demonstrate that MARO achieves significant improvements over existing methods. Multi-Dimensional Analysis Module Decision Rule Validation ModuleWow, this sounds amazing ... .

Metaphor detection, a critical task in natural language processing, involves identifying whether a particular word in a sentence is used metaphorically. Traditional approaches often rely on supervised learning models that implicitly encode semantic relationships based on metaphor theories. However, these methods often suffer from a lack of transparency in their decision-making processes, which undermines the reliability of their predictions. Recent research indicates that LLMs (large language models) exhibit significant potential in metaphor detection. Nevertheless, their reasoning capabilities are constrained by predefined knowledge graphs. To overcome these limitations, we propose DMD, a novel dual-perspective framework that harnesses both implicit and explicit applications of metaphor theories to guide LLMs in metaphor detection and adopts a self-judgment mechanism to validate the responses from the aforementioned forms of guidance. In comparison to previous methods, our framework offers more transparent reasoning processes and delivers more reliable predictions. Experimental results prove the effectiveness of DMD, demonstrating state-of-the-art performance across widely-used datasets.

Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A potential cause is the scarcity of visual knowledge in popular instruction-tuning corpora, resulting in inadequate visual perception and reasoning capabilities. To address this challenge, we introduce a self-improvement framework grounded in a novel visual knowledge-intensive task, Causality-driven Visual object Completion (CVC). This task requires LVLMs to infer the masked object in an image based on its causal relationships with the other visible information. We first obtain rich examples cheaply through our automated instance construction pipeline, without relying on sophisticated LVLMs (e.g., GPT-4V) or human assistance. Then, LVLMs effectively self-improve through trial and error learning using these created instances. Our experiments demonstrate substantial gains across four challenging specialized tasks and four widely-used comprehensive benchmarks. Especially on specialized tasks, our method achieves an average improvement of 5.4% and 4.0% compared to the corresponding baselines when utilizing LLaVA-1.5-7B and LLaVA-1.5-13B, respectively. Code and the supplementary file are available at https://github.com/XMUDeepLIT/CVC.

Recently, video editing task has gained widespread attention due to its practical applications and rapid advancements. However, current automatic evaluation metrics for video editing are mostly poorly aligned with human judgments. Thus, researchers heavily rely on human evaluation, which is not only labor-intensive but also difficult to ensure consistency and objectivity. To address these issues, we propose EditEval, the largest-ever video editing benchmark to comprehensively evaluate the performance of video editing models in three aspects: Textual Faithfulness, Frame Consistency, and Video Fidelity. It includes 200 video clips and 1,010 text prompts, from which 160 instances are sampled to generate 1,280 edited videos using eight open-source video editing models, accompanied by human annotations. Furthermore, we propose EditScore, leveraging the advanced reasoning and comprehension capabilities of Multi-modal Large Language Models (MLLMs) as evaluators to assess edited videos across the aforementioned aspects. Experiments show that the best-performing video editing model only reaches an average score of 3.16 (out of a perfect 5), highlighting the challenge of EditEval. Besides, results from more than 10 MLLMs demonstrate the great potential of utilizing EditScore for automatic evaluation. Notably, for textual faithfulness, EditScore equipped with LLaVA-OneVision-7B achieves a significantly higher Pearson Correlation score compared to previous methods based on CLIP (0.50 vs 0.22). The code and dataset are available at: https://github.com/XMUDeepLIT/EditEval

Leveraging vast and continually updated knowledge from the Internet has been considered an important ability for a dialogue system. Therefore, the dialogue query generation task is proposed for generating search queries from dialogue histories, which will be submitted to a search engine for retrieving relevant websites on the Internet. In this regard, previous efforts were devoted to collecting conversations with annotated queries and training a query producer (QP) via standard supervised learning. However, these studies still face the challenges of data scarcity and domain adaptation. To address these issues, in this paper, we propose a semi-supervised learning framework -- SemiDQG, to improve model performance with unlabeled conversations. Based on the observation that the search query is typically related to the topic of dialogue response, we train a response-augmented query producer (RA) to provide rich and effective training signals for QP. We first apply a similarity-based query selection strategy to select high-quality RA-generated pseudo queries, which are used to construct pseudo instances for training QP and RA. Then, we adopt the REINFORCE algorithm to further enhance QP, with RA-provided rewards as fine-grained training signals. Experimental results and in-depth analysis of three benchmarks show the effectiveness of our framework in cross-domain and low-resource scenarios. Particularly, SemiDQG significantly surpasses ChatGPT and competitive baselines. Our code is available at \url{https://github.com/DeepLearnXMU/SemiDQG}.

Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

In an emotional conversation, emotions are causally transmitted among communication participants, constituting a fundamental conversational feature that can facilitate the comprehension of intricate changes in emotional states during the conversation and contribute to neutralizing emotional semantic bias in utterance caused by the absence of modality information. Therefore, emotional transition (ET) plays a crucial role in the task of Emotion Recognition in Conversation (ERC) that has not received sufficient attention in current research. In light of this, an Emotional Transition-based Emotion Recognizer (EmoTrans) is proposed in this paper. Specifically, we concatenate the most recent utterances with their corresponding speakers to construct the model input, known as samples, each with several placeholders to implicitly express the emotions of contextual utterances. Based on these placeholders, two components are developed to make the model sensitive to emotions and effectively capture the ET features in the sample. Furthermore, an ET-based Contrastive Learning (CL) is developed to compact the representation space, making the model achieve more robust sample representations. We conducted exhaustive experiments on four widely used datasets and obtained competitive experimental results, especially, new state-of-the-art results obtained on MELD and IEMOCAP, demonstrating the superiority of EmoTrans.

In document-level relation extraction (RE), the models are required to correctly predict implicit relations in documents via relational reasoning. To this end, many graph-based methods have been proposed for this task. Despite their success, these methods still suffer from several drawbacks: 1) their interaction between document encoder and graph encoder is usually unidirectional and insufficient; 2) their graph encoders often fail to capture the global context of nodes in document graph. In this paper, we propose a document-level RE model with a Graph-Transformer Network (GTN). The GTN includes two core sublayers: 1) the graph-attention sublayer that simultaneously models global and local contexts of nodes in the document graph; 2) the cross-attention sublayer, enabling GTN to capture the non-entity clue information from the document encoder. Furthermore, we introduce two auxiliary training tasks to enhance the bidirectional semantic interaction between the document encoder and GTN: 1) the graph node reconstruction that can effectively train our cross-attention sublayer to enhance the semantic transition from the document encoder to GTN; 2) the structure-aware adversarial knowledge distillation, by which we can effectively transfer the structural information of GTN to the document encoder. Experimental results on four benchmark datasets prove the effectiveness of our model. Our source code is available at https://github.com/DeepLearnXMU/DocRE-BSI.

Abstract We focus on the factuality property during the extraction of an OpenIE corpus named OpenFact, which contains more than 12 million high-quality knowledge triplets. We break down the factuality property into two important aspects—expressiveness and groundedness—and we propose a comprehensive framework to handle both aspects. To enhance expressiveness, we formulate each knowledge piece in OpenFact based on a semantic frame. We also design templates, extra constraints, and adopt human efforts so that most OpenFact triplets contain enough details. For groundedness, we require the main arguments of each triplet to contain linked Wikidata1 entities. A human evaluation suggests that the OpenFact triplets are much more accurate and contain denser information compared to OPIEC-Linked (Gashteovski et al., 2019), one recent high-quality OpenIE corpus grounded to Wikidata. Further experiments on knowledge base completion and knowledge base question answering show the effectiveness of OpenFact over OPIEC-Linked as supplementary knowledge to Wikidata as the major KG.

Conversational discourse analysis aims to extract the interactions between dialogue turns, which is crucial for modeling complex multi-party dialogues. As the benchmarks are still limited in size and human annotations are costly, the current standard approaches apply pretrained language models, but they still require randomly initialized classifiers to make predictions. These classifiers usually require massive data to work smoothly with the pretrained encoder, causing severe data hunger issue. We propose two convenient strategies to formulate this task as a sequence generation problem, where classifier decisions are carefully converted into sequence of tokens. We then adopt a pretrained T5 1 model to solve this task so that no parameters are randomly initialized. We also leverage the descriptions of the discourse relations to help model understand their meanings. Experiments on two popular benchmarks show that our approach outperforms previous state-of-the-art models by a large margin, and it is also more robust in zero-shot and few-shot settings.

Dialogue understanding has always been a bottleneck for many conversational tasks, such as dialogue response generation and conversational question answering. To expedite the progress in this area, we introduce the task of conversational aspect sentiment analysis (CASA) that can provide useful fine-grained sentiment information for dialogue understanding and planning. Overall, this task extends the standard aspect-based sentiment analysis to the conversational scenario with several major adaptations. To aid the training and evaluation of data-driven methods, we annotate 3,000 chit-chat dialogues (27,198 sentences) with fine-grained sentiment information, including all sentiment expressions, their polarities and the corresponding target mentions. We also annotate an out-of-domain test set of 200 dialogues for robustness evaluation. Besides, we develop multiple baselines based on either pretrained BERT or self-attention for preliminary study. Experimental results show that our BERT-based model has strong performances for both in-domain and out-of-domain datasets, and thorough analysis indicates several potential directions for further improvements.

Yubin Ge, Ly Dinh, Xiaofeng Liu, Jinsong Su, Ziyao Lu, Ante Wang, Jana Diesner. 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.

Shaopeng Lai, Ante Wang, Fandong Meng, Jie Zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang, Jinsong Su. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

Conversational discourse structures aim to describe how a dialogue is organized, thus they are helpful for dialogue understanding and response generation. This paper focuses on predicting discourse dependency structures for multi-party dialogues. Previous work adopts incremental methods that take the features from the already predicted discourse relations to help generate the next one. Although the inter-correlations among predictions considered, we find that the error propagation is also very serious and hurts the overall performance. To alleviate error propagation, we propose a Structure Self-Aware (SSA) model, which adopts a novel edge-centric Graph Neural Network (GNN) to update the information between each Elementary Discourse Unit (EDU) pair layer by layer, so that expressive representations can be learned without historical predictions. In addition, we take auxiliary training signals (e.g. structure distillation) for better representation learning. Our model achieves the new state-of-the-art performances on two conversational discourse parsing benchmarks, largely outperforming the previous methods.

The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs.As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs when generating outputs.We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information.In particular, we introduce two types of autoencoding losses, each individually focusing on different aspects (a.k.a.views) of input graphs.The losses are then back-propagated to better calibrate our model via multi-task training.Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline.Our code is available at http://github.com/ Soistesimmer/AMR-multiview.