Yuzhe Zhang, Feiran Liu, Yi Shan, Xinyi Huang, Xin Yang, Yueqi Zhu, Xuxin Cheng, Cao Liu, Ke Zeng, Terry Jingchen Zhang, Wenyuan Jiang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large language models (LLMs) have recently been adopted for recommendation by framing user preference modeling as a language generation problem. However, existing latent reasoning approaches typically represent user intent with a single latent vector, which struggles to capture the inherently multi-faceted nature of user preferences. We propose Factorized Latent Reasoning (FLR), a novel framework for LLM-based sequential recommendation that decomposes latent reasoning into multiple disentangled preference factors. FLR introduces a lightweight multi-factor attention module that iteratively refines a latent thought representation, where each factor attends to distinct aspects of the user's interaction history. To encourage diversity and specialization, we design orthogonality, attention diversity, and sparsity regularization objectives, and dynamically aggregate factor contributions for the final prediction. We further integrate FLR with an efficient reinforcement learning strategy based on group-relative policy optimization, enabling stable alignment directly in the latent reasoning space. Experiments on multiple benchmarks show that FLR consistently outperforms strong baselines while improving robustness and interpretability. Our data and code are available at https://github.com/ToAdventure/FLR.

Mengjie Ren, Boxi Cao, Hongyu Lin, Cao Liu, Xianpei Han, Ke Zeng, Wan Guanglu, Xunliang Cai, Le Sun. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Multi-label unknown intent detection is a challenging task where each utterance may contain not only multiple known but also unknown intents. To tackle this challenge, pioneers proposed to predict the intent number of the utterance first, then compare it with the results of known intent matching to decide whether the utterence contains unknown intent(s). Though they have made remarkable progress on this task, their methods still suffer from two important issues: (1) It is inadequate to extract multiple intents using only utterance encoding; (2) Optimizing two sub-tasks (intent number prediction and known intent matching) independently leads to inconsistent predictions. In this article, we propose to incorporate segment augmentation rather than only use utterance encoding to better detect multiple intents. We also design a prediction consistency module to bridge the gap between the two sub-tasks. Empirical results on MultiWOZ2.3 and MixSNIPS datasets show that our method achieves state-of-the-art performance and significantly improves the best baseline.

Shan Wu, Chunlei Xin, Hongyu Lin, Xianpei Han, Cao Liu, Jiansong Chen, Fan Yang, Guanglu Wan, Le Sun. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Multi-label unknown intent detection is a challenging task where each utterance may contain not only multiple known but also unknown intents. To tackle this challenge, pioneers proposed to predict the intent number of the utterance first, then compare it with the results of known intent matching to decide whether the utterance contains unknown intent(s). Though they have made remarkable progress on this task, their method still suffers from two important issues: 1) It is inadequate to extract multiple intents using only utterance encoding; 2) Optimizing two sub-tasks (intent number prediction and known intent matching) independently leads to inconsistent predictions. In this paper, we propose to incorporate segment augmentation rather than only use utterance encoding to better detect multiple intents. We also design a prediction consistency module to bridge the gap between the two sub-tasks. Empirical results on MultiWOZ2.3 show that our method achieves state-of-the-art performance and improves the best baseline significantly.

Although In-Context Learning has proven effective across a broad array of tasks, its efficiency is noticeably influenced by the selection of demonstrations.Existing methods tend to select different demonstrations for each test instance, which is time-consuming and poses limitations in practical scenarios.Therefore, this study aims to address the challenge of selecting a representative subset of in-context demonstrations that can effectively prompt different test instances in a specific task.We propose that this representative subset should be of high quality and diversity.Our empirical analyses confirm that demonstrations that meet these criteria can indeed bolster model performance.To satisfy these criteria, this paper further introduces a two-stage Determinantal Point Process (DPP) method designed to incorporate both quality and diversity in the process of demonstration selection, thereby obtaining representative in-context demonstrations.Through comprehensive experimentation, we have confirmed the efficacy of our proposed method, paving the way for more practical and effective In-Context Learning.

Data-driven methods have achieved notable performance on intent detection, which is a task to comprehend user queries. Nonetheless, they are controversial for over-confident predictions. In some scenarios, users do not only care about the accuracy but also the confidence of model. Unfortunately, mainstream neural networks are poorly calibrated, with a large gap between accuracy and confidence. To handle this problem defined as confidence calibration, we propose a model using the hyperspherical space and rebalanced accuracy-uncertainty loss. Specifically, we project the label vector onto hyperspherical space uniformly to generate a dense label representation matrix, which mitigates over-confident predictions due to overfitting sparse one-hot label matrix. Besides, we rebalance samples of different accuracy and uncertainty to better guide model training. Experiments on the open datasets verify that our model outperforms the existing calibration methods and achieves a significant improvement on the calibration metric.

Dialogue topic segmentation is a challenging task in which dialogues are split into segments with pre-defined topics. Existing works on topic segmentation adopt a two-stage paradigm, including text segmentation and segment labeling. However, such methods tend to focus on the local context in segmentation, and the inter-segment dependency is not well captured. Besides, the ambiguity and labeling noise in dialogue segment bounds bring further challenges to existing models. In this work, we propose the Parallel Extraction Network with Neighbor Smoothing (PEN-NS) to address the above issues. Specifically, we propose the parallel extraction network to perform segment extractions, optimizing the bipartite matching cost of segments to capture inter-segment dependency. Furthermore, we propose neighbor smoothing to handle the segment-bound noise and ambiguity. Experiments on a dialogue-based and a document-based topic segmentation dataset show that PEN-NS outperforms state-the-of-art models significantly.

Pre-trained language models have achieved noticeable performance on the intent detection task. However, due to assigning an identical weight to each sample, they suffer from the overfitting of simple samples and the failure to learn complex samples well. To handle this problem, we propose a density-based dynamic curriculum learning model. Our model defines the sample's difficulty level according to their eigenvectors' density. In this way, we exploit the overall distribution of all samples' eigenvectors simultaneously. Then we apply a dynamic curriculum learning strategy, which pays distinct attention to samples of various difficulty levels and alters the proportion of samples during the training process. Through the above operation, simple samples are well-trained, and complex samples are enhanced. Experiments on three open datasets verify that the proposed density-based algorithm can distinguish simple and complex samples significantly. Besides, our model obtains obvious improvement over the strong baselines.

Dialogue state tracking (DST), which estimates user goals given a dialogue context, is an essential component of task-oriented dialogue systems.Conventional DST models are usually trained offline, which requires a fixed dataset prepared in advance.This paradigm is often impractical in real-world applications since online dialogue systems usually involve continually emerging new data and domains.Therefore, this paper explores Domain-Lifelong Learning for Dialogue State Tracking (DLL-DST), which aims to continually train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains.To this end, we propose a novel domainlifelong learning method, called Knowledge Preservation Networks (KPN), which consists of multi-prototype enhanced retrospection and multi-strategy knowledge distillation, to solve the problems of expression diversity and combinatorial explosion in the DLL-DST task.Experimental results show that KPN effectively alleviates catastrophic forgetting and outperforms previous state-of-the-art lifelong learning methods by 4.25% and 8.27% of whole joint goal accuracy on the MultiWOZ benchmark and the SGD benchmark, respectively.

Given a long text, the summarization system aims to obtain a shorter highlight while keeping important information on the original text. For customer service, the summaries of most dialogues between an agent and a user focus on several fixed key points, such as user's question, user's purpose, the agent's solution, and so on. Traditional extractive methods are difficult to extract all predefined key points exactly. Furthermore, there is a lack of large-scale and high-quality extractive summarization datasets containing key points. In order to solve the above challenges, we propose a Distant Supervision based Machine Reading Comprehension model for extractive Summarization (DSMRC-S). DSMRC-S transforms the summarization task into the machine reading comprehension problem, to fetch key points from the original text exactly according to the predefined questions. In addition, a distant supervision method is proposed to alleviate the lack of eligible extractive summarization datasets. We conduct experiments on a large-scale summarization dataset collected in customer service scenarios, and the results show that the proposed DSMRC-S outperforms the strong baseline methods by 4 points on ROUGE-L.

We study the task of response generation.Conventional methods employ a fixed vocabulary and one-pass decoding, which not only make them prone to safe and general responses but also lack further refining to the first generated raw sequence.To tackle the above two problems, we present a Vocabulary Pyramid Network (VPN) which is able to incorporate multi-pass encoding and decoding with multi-level vocabularies into response generation.Specifically, the dialogue input and output are represented by multi-level vocabularies which are obtained from hierarchical clustering of raw words.Then, multi-pass encoding and decoding are conducted on the multilevel vocabularies.Since VPN is able to leverage rich encoding and decoding information with multi-level vocabularies, it has the potential to generate better responses.Experiments on English Twitter and Chinese Weibo datasets demonstrate that VPN remarkably outperforms strong baselines.

Conventional chatbots focus on two-party response generation, which simplifies the real dialogue scene.In this paper, we strive toward a novel task of Response Generation on Multi-Party Chatbot (RGMPC), where the generated responses heavily rely on the interlocutors' roles (e.g., speaker and addressee) and their utterances.Unfortunately, complex interactions among the interlocutors' roles make it challenging to precisely capture conversational contexts and interlocutors' information.Facing this challenge, we present a response generation model which incorporates Interlocutor-aware Contexts into Recurrent Encoder-Decoder frameworks (ICRED) for RGMPC.Specifically, we employ interactive representations to capture dialogue contexts for different interlocutors.Moreover, we leverage an addressee memory to enhance contextual interlocutor information for the target addressee.Finally, we construct a corpus for RGMPC based on an existing open-access dataset.Automatic and manual evaluations demonstrate that the ICRED remarkably outperforms strong baselines.

Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

By reason of being able to obtain natural language responses, natural answers are more favored in real-world Question Answering (QA) systems. Generative models learn to automatically generate natural answers from large-scale question answer pairs (QA-pairs). However, they are suffering from the uncontrollable and uneven quality of QA-pairs crawled from the Internet. To address this problem, we propose a curriculum learning based framework for natural answer generation (CL-NAG), which is able to take full advantage of the valuable learning data from a noisy and uneven-quality corpus. Specifically, we employ two practical measures to automatically measure the quality (complexity) of QA-pairs. Based on the measurements, CL-NAG firstly utilizes simple and low-quality QA-pairs to learn a basic model, and then gradually learns to produce better answers with richer contents and more complete syntaxes based on more complex and higher-quality QA-pairs. In this way, all valuable information in the noisy and uneven-quality corpus could be fully exploited. Experiments demonstrate that CL-NAG outperforms the state-of-the-arts, which increases 6.8% and 8.7% in the accuracy for simple and complex questions, respectively.

Generating answer with natural language sentence is very important in real-world question answering systems, which needs to obtain a right answer as well as a coherent natural response.In this paper, we propose an end-to-end question answering system called COREQA in sequence-to-sequence learning, which incorporates copying and retrieving mechanisms to generate natural answers within an encoder-decoder framework.Specifically, in COREQA, the semantic units (words, phrases and entities) in a natural answer are dynamically predicted from the vocabulary, copied from the given question and/or retrieved from the corresponding knowledge base jointly.Our empirical study on both synthetic and realworld datasets demonstrates the efficiency of COREQA, which is able to generate correct, coherent and natural answers for knowledge inquired questions.