China

Large language models (LLMs) have demonstrated remarkable performance in zero-shot dialogue state tracking (DST), reducing the need for task-specific training. However, conventional DST benchmarks primarily focus on structured user-agent conversations, failing to capture the complexities of real-world multi-user interactions. In this study, we assess the robustness of LLMs in multi-user DST while minimizing dataset construction costs. Inspired by recent advances in LLM-based data annotation, we extend an existing DST dataset by generating utterances of a second user based on speech act theory. Our methodology systematically incorporates a second user’s utterances into conversations, enabling a controlled evaluation of LLMs in multi-user settings. Experimental results reveal a significant performance drop compared to single-user DST, highlighting the limitations of current LLMs in extracting and tracking dialogue states amidst multiple speakers. Our findings emphasize the need for future research to enhance LLMs for multi-user DST scenarios, paving the way for more realistic and robust DST models.

EMNLP 2025

Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models

poster

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community."<br>

*Message from the General Chair, Dirk Hovy*

[**Link to Conference Handbook**](https://drive.google.com/file/d/1johU5QqVVYO4RfH7QcIORr7qrVBdzdwC/view?usp=sharing)





<br>

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

Automatic open-domain dialogue evaluation has attracted increasing attention, yet remains challenging due to the complexity of assessing response appropriateness. Traditional evaluation metrics, typically trained with true positive and randomly selected negative responses, tend to assign higher scores to responses that share greater content similarity with contexts. However, adversarial negative responses, despite possessing high lexical overlap with contexts, can be semantically incongruous. Consequently, existing metrics struggle to evaluate such responses effectively, resulting in low correlations with human judgments. While recent studies have demonstrated the effectiveness of Large Language Models (LLMs) for open-domain dialogue evaluation, they still face challenges in handling adversarial negative examples. We propose a novel evaluation framework that integrates Abstract Meaning Representation (AMR) enhanced domain-specific language models (SLMs) with LLMs. Our SLMs explicitly incorporate AMR graph information through a gating mechanism for enhanced semantic representation learning, while both SLM predictions and AMR knowledge are integrated into LLM prompts for robust evaluation. Extensive experiments on open-domain dialogue evaluation tasks demonstrate the superiority of our method compared to state-of-the-art baselines, particularly in discriminating adversarial negative responses. Our framework achieves strong correlations with human judgments across multiple datasets, establishing a new benchmark for dialogue evaluation. Our code and data are publicly available.

Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation

Multimodal Knowledge Graphs (MMKGs) enhance knowledge representations by integrating structural and multimodal information of entities. Recently, MMKGs have proven effective in tasks such as information retrieval, knowledge discovery, and question answering. Current methods typically utilize pre-trained visual encoders to extract features from images associated with each entity, emphasizing complex cross-modal interactions. However, these approaches often overlook the varying relevance of visual information across entities. Specifically, not all entities benefit from visual data, and not all associated images are pertinent, with irrelevant images introducing noise and potentially degrading model performance. To address these issues, we propose the Differentiated Vision for Multimodal Knowledge Graphs (DVMKG) model. DVMKG evaluates the necessity of visual modality for each entity based on its intrinsic attributes and assesses image quality through representativeness and diversity. Leveraging these metrics, DVMKG dynamically adjusts the influence of visual data during feature integration, tailoring it to the specific needs of different entity types. Extensive experiments on multiple benchmark datasets confirm the effectiveness of DVMKG, demonstrating significant improvements over existing methods.

Differentiated Vision: Unveiling Entity-Specific Visual Modality Requirements for Multimodal Knowledge Graph

Large language models (LLMs) have been able to perform various forms of reasoning tasks in a wide range of scenarios, but are they truly engaging in task abstraction and rule-based reasoning beyond mere memorization? To answer this question, we propose a novel experimental approach, Misleading Fine-Tuning (MisFT), to examine whether LLMs perform abstract reasoning by altering their original understanding of fundamental rules. In particular, by constructing datasets with math expressions or logical formulas that contradict correct principles, we fine-tune the model to learn those contradictory rules and assess its generalization ability on unseen test domains. Through a series of experiments, we find that current LLMs are capable of applying contradictory rules to solve practical math word problems and natural language reasoning tasks, implying the presence of an internal mechanism in LLMs that abstracts before reasoning.

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them

Abusive language online creates toxic environments and exacerbates social tensions, underscoring the need for robust NLP models to interpret nuanced linguistic cues. This paper introduces GAttention, a novel Gated Attention mechanism that combines the strengths of Contextual attention and Self-attention mechanisms to address the limitations of existing attention models within the text classification task. GAttention capitalizes on local and global query vectors by integrating the internal relationships within a sequence (Self-attention) and the global relationships among distinct sequences (Contextual attention). This combination allows for a more nuanced understanding and processing of sequence elements, which is particularly beneficial in context-sensitive text classification tasks such as the case of abusive language detection. By applying this mechanism to transformer-based encoder models, we showcase how it enhances the model's ability to discern subtle nuances and contextual clues essential for identifying abusive language, a challenging and increasingly relevant task within NLP.

GAttention: Gated Attention for the Detection of Abusive Language

As language models have a greater impact on society, it is important to ensure they are aligned to a diverse range of perspectives and are able to reflect nuance in human values. However, the most popular training paradigms for modern language models often assume there is one optimal answer for every query, leading to generic responses and poor alignment. In this work, we aim to enhance pluralistic alignment of language models in a low-resource setting with two methods: pluralistic decoding and model steering. We empirically demonstrate that model steering offers consistent improvement over zero-shot and few-shot baselines with only 50 annotated samples. Our proposed methods decrease false positives in several high-stakes tasks such as hate speech detection and misinformation detection, and improves the distributional alignment to human values from different demographics. We hope our work highlights the importance of diversity and how language models can be adapted to consider nuanced perspectives.

Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback

Domain-specific quantitative reasoning remains a major challenge for Large Language Models (LLMs), especially in fields requiring expert knowledge and complex question answering (QA). In this work, we propose Expert Question Decomposition (EQD), an approach designed to balance the use of domain knowledge with computational efficiency. EQD is built on a two-step fine-tuning framework and guided by a reward function that measures the effectiveness of generated sub-questions in improving QA outcomes. It requires only a few thousand training examples and a single A100 GPU for fine-tuning, with inference time comparable to zero-shot prompting. Beyond its efficiency, EQD outperforms state-of-the-art domain-tuned models and advanced prompting strategies. We evaluate EQD in the financial domain, characterized by specialized knowledge and complex quantitative reasoning, across four benchmark datasets. Our method consistently improves QA performance by 0.6% to 10.5% across different LLMs. Our analysis reveals an important insight: in domain-specific QA, a single critical supporting question often provide greater benefit than detailed guidance steps.

One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoning

Large Language Models (LLMs) have shown promising performance on diverse medical benchmarks, highlighting their potential in supporting real-world clinical tasks. Retrieval-Augmented Generation (RAG) has emerged as a key approach for mitigating knowledge gaps and hallucinations by incorporating external medical information. However, RAG still struggles with complex medical questions that require intensive reasoning, as surface-level input often fails to reflect the true knowledge needs of the task. Existing methods typically focus on refining queries without explicitly modeling the reasoning process, limiting their ability to retrieve and integrate clinically relevant knowledge. In this work, we propose RAR², a joint learning framework that improves both Reasoning-Augmented Retrieval and Retrieval-Augmented Reasoning. RAR² constructs a thought process to uncover implicit knowledge requirements and uses it to guide retrieval and answer generation. We build a training dataset of mixed preference pairs and apply Direct Preference Optimization (DPO) to train the model. Moreover, we design two test-time scaling strategies to explore the boundaries of our framework. Experiments demonstrate the effectiveness of RAR² across several biomedical question answering datasets, outperforming RAG baselines with or without fine-tuning.

RAR²: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval

The choice of a suitable visual language projector (VLP) is critical to the successful training of large visual language models (LVLMs). Mainstream VLPs can be broadly categorized into compressed and uncompressed projectors, and each offering distinct advantages in performance and computational efficiency. However, their security implications have not been thoroughly examined. Our comprehensive evaluation reveals significant differences in their security profiles: compressed projectors exhibit substantial vulnerabilities, allowing adversaries to successfully compromise LVLMs even with minimal knowledge of structural information. In stark contrast, uncompressed projectors demonstrate robust security properties and do not introduce additional vulnerabilities. These findings provide critical guidance for researchers in selecting optimal VLPs that enhance the security and reliability of visual language models. The code will be released.

The Security Threat of Compressed Projectors in Large Vision-Language Models

The behavior of Large Language Models (LLMs) when facing contextual information that conflicts with their internal parametric knowledge is inconsistent, with no generally accepted explanation for the expected outcome distribution. Recent work has identified in autoregressive transformer models a class of neurons -- called textitentropy neurons -- that produce a significant effect on the model output entropy while having an overall moderate impact on the ranking of the predicted tokens. In this paper, we investigate the preliminary claim that these neurons are involved in inhibiting context copying behavior in transformers by looking at their role in resolving conflicts between contextual and parametric information. We show that textitentropy neurons are responsible for suppressing context copying across a range of LLMs, and that ablating them leads to a significant change in the generation process. These results enhance our understanding of the internal dynamics of LLMs when handling conflicting information.

Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge Conflicts

Rhetorical strategies are central to persuasive communication, from political discourse and marketing to legal argumentation. However, analysis of rhetorical strategies has been limited by reliance on human annotation, which is costly, inconsistent, difficult to scale. Their associated datasets are often limited to specific topics and strategies, posing challenges for robust model development. We propose a novel framework that leverages large language models (LLMs) to automatically generate and label synthetic debate data based on a four-part rhetorical typology (causal, empirical, emotional, moral). We fine-tune transformer-based classifiers on this LLM-labeled dataset and validate its performance against human-labeled data on this dataset and on multiple external corpora. Our model achieves high performance and strong generalization across topical domains. We illustrate two applications with the fine-tuned model: (1) the improvement in persuasiveness prediction from incorporating rhetorical strategy labels, and (2) analyzing temporal and partisan shifts in rhetorical strategies in U.S. Presidential debates (1960–2020), revealing increased use of affective over cognitive argument in U.S. Presidential debates.

Downloads

Next from EMNLP 2025

Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES