China

We examine how multimodal large language models (MLLMs) perform logical inference grounded in visual information. We first construct a dataset of food web/chain images, along with questions that follow seven structured templates with progressively more complex reasoning involved. We show that complex reasoning about entities in the images remains challenging (even with elaborate prompts) and that visual information is underutilized.

EMNLP 2025

Probing Logical Reasoning of MLLMs in Scientific Diagrams

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.

Video question answering benefits from the rich information available in videos, enabling a wide range of applications. However, the large volume of tokens generated from longer videos presents significant challenges to memory efficiency and model performance. To alleviate this issue, existing works propose to compress video inputs, but usually overlooking the varying importance of static and dynamic information across different queries, leading to inefficient token usage within limited budgets. To tackle this, we propose a novel token selection strategy, \textsc{explore-then-select}, that adaptively adjust static and dynamic information needed based on question requirements. Our framework first explores different token allocations between key frames, which preserve spatial details, and delta frames, which capture temporal changes. Next, it employs a query-aware attention-based metric to select the optimal token combination without model updates. Our proposed framework is plug-and-play that can be seamlessly integrated within diverse video-language models. Extensive experiments show that our method achieves significant performance improvements (up to 5.8%) among various video question answering benchmarks. The code is accessible at the anonymous \href{https://anonymous.4open.science/r/Static\_Or\_Dynamic}{link}.

Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering

Discharge communication is a critical yet underexplored component of patient care, where the goal shifts from diagnosis to education. While recent LLM benchmarks emphasize in-visit diagnostic reasoning, they fail to evaluate models’ ability to support patients after the visit. We introduce DischargeSim, a novel benchmark that evaluates large language models (LLMs) on their ability to act as personalized discharge educators. DischargeSim simulates post-visit, multi-turn conversations between LLM-driven DoctorAgents and PatientAgents with diverse psychosocial profiles (e.g., health literacy, education, emotion). Interactions are structured across six clinically grounded discharge topics and assessed along three axes: (1) dialogue quality via automatic and LLM-as-judge evaluation, (2) personalized document generation including free-text summaries and structured AHRQ checklists, and (3) patient comprehension through a downstream multiple-choice exam. Experiments across 17 LLMs reveal significant gaps in discharge education capability, with performance varying widely across patient profiles. Notably, model size does not always yield better education outcomes—highlighting trade-offs in strategy use and content prioritization. DischargeSim offers a first step toward benchmarking LLMs in post-visit clinical education and promoting equitable, personalized patient support.

DischargeSim: A Simulation Benchmark for Educational Doctor–Patient Communication at Discharge

Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation solving, where mathematical equations are embedded in images, variables are represented by object icons, and coefficients must be inferred by counting. While VLMs perform well on textual equations, they fail on visually grounded counterparts. To understand this gap, we decompose the task into coefficient counting and variable recognition, and find that counting is the primary bottleneck, even when recognition is accurate. We also observe that composing recognition and reasoning introduces additional errors, highlighting challenges in multistep visual reasoning. Finally, as equation complexity increases, symbolic reasoning itself becomes a limiting factor. These findings reveal key weaknesses in current VLMs and point toward future improvements in visually grounded mathematical reasoning.

Can Vision-Language Models Solve Visual Math Equations?

Retrieval-augmented generation (RAG) is a cost-effective approach to mitigate the hallucination of Large Language Models (LLMs) by incorporating the retrieved external knowledge into the generation process. However, external knowledge may conflict with the parametric knowledge of LLMs. Furthermore, current LLMs lack inherent mechanisms for resolving such knowledge conflicts, making traditional RAG methods suffer from degraded performance and stability. Thus, we propose a Dual-Stream Knowledge-Augmented Framework for Shared-Private Semantic Synergy (DSSP-RAG). Central to the framework is a novel approach that refines self-attention into a mixed-attention, distinguishing shared and private semantics for a controlled internal-external knowledge integration. To effectively facilitate DSSP in RAG, we further introduce an unsupervised hallucination detection method based on cognitive uncertainty, ensuring the necessity of introducing knowledge, and an Energy Quotient (EQ) based on attention difference matrices to reduce noise in the retrieved external knowledge. Extensive experiments on benchmark datasets show that DSSP-RAG can effectively resolve conflicts and enhance the complementarity of dual-stream knowledge, leading to superior performance over strong baselines.

Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge

Multimodal Sentiment Analysis (MSA) is the task of understanding human emotions by analyzing a combination of different data sources, such as text, audio, and visual inputs. Although recent advances have improved emotion modeling across modalities, existing methods still struggle with two fundamental challenges: balancing global and fine-grained sentiment contributions, and over-reliance on the text modality. To address these issues, we propose DPDF-LQ (Dual-Path Dynamic Fusion with Learnable Query), an architecture that processes inputs through two complementary paths: global and local. The global path is responsible for establishing cross-modal dependencies, while the local path captures fine-grained representations. Additionally, we introduce the key module Dynamic Global Learnable Query Attention (DGLQA) in the global path, which dynamically allocates weights to each modality to capture their relevant features and learn global representations. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that DPDF-LQ achieves state-of-the-art performance, particularly in fine-grained sentiment prediction, by effectively combining global and local features.

Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis

Complex multi-step reasoning remains challenging for large language models (LLMs). While parallel inference-time scaling methods, such as step-level beam search, offer a promising solution, existing approaches typically depend on either domain-specific external verifiers, or self-evaluation which is brittle and prompt-sensitive. To address these issues, we propose Collaborative Beam Search (CBS), an iterative framework that harnesses the collective intelligence of multiple LLMs across both generation and verification stages. For generation, CBS leverages multiple LLMs to explore a broader search space, resulting in more diverse candidate steps. For verifications, CBS employs a perplexity-based collective consensus among these models, eliminating reliance on an external verifier or complex prompts. Between iterations, CBS leverages a dynamic quota allocation strategy that reassigns generation budget based on each model’s past consensus performance, striking a balance between candidate diversity and quality. Experimental results on six tasks across arithmetic, logical, and commonsense reasoning show that CBS outperforms single‑model scaling and multi-model ensemble baselines by over 4 percentage points in average accuracy, demonstrating its effectiveness and broad applicability.

Collaborative Beam Search: Enhancing LLM Reasoning via Collective Consensus

Instruction tuning in multimodal large language models (MLLMs) generally involves cooperative learning between a backbone LLM and a feature encoder of non-text input modalities. The major challenge is how to efficiently find the synergy between the two modules so that LLMs can adapt their reasoning abilities to downstream tasks while feature encoders can adjust to provide more task-specific information about its modality. In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives, where we find the unbalanced learning between the feature encoder and the LLM can cause problems of oscillation and biased learning that lead to sub-optimal convergence. Inspired by our findings, we propose a Multimodal Balance Coefficient that enables quantitative measurement of the balance of learning. Based on this, we further design a dynamic learning scheduler that better coordinates the learning between the LLM and feature encoder, alleviating the problems of oscillation and biased learning. In addition, we introduce an auxiliary regularization on the gradient to promote updating with larger step sizes, which potentially allows for a more accurate estimation of the proposed MultiModal Balance Coefficient and further improves the training sufficiency. Our proposed approach is agnostic to the architecture of LLM and feature encoder, so it can be generically integrated with various MLLMs. We conduct experiments on multiple downstream tasks with various MLLMs, demonstrating that the proposed method is more effective than the baselines in MLLM instruction tuning.

CoMMIT: Coordinated Multimodal Instruction Tuning

We introduce CEMTM, a context-enhanced multimodal topic model designed to infer coherent and interpretable topic structures from both short and long documents containing text and images. CEMTM builds on fine-tuned large vision language models (LVLMs) to obtain contextualized embeddings, and employs a distributional attention mechanism to weight token-level contributions to topic inference. A reconstruction objective aligns topic-based representations with the document embedding, encouraging semantic consistency across modalities. Unlike existing approaches, CEMTM can process multiple images per document without repeated encoding and maintains interpretability through explicit word-topic and document-topic distributions. Extensive experiments on six multimodal benchmarks show that CEMTM consistently outperforms unimodal and multimodal baselines, achieving a remarkable average LLM score of 2.61. Further analysis shows its effectiveness in downstream few-shot retrieval and its ability to capture visually grounded semantics in complex domains such as scientific articles.

CEMTM: Contextual Embedding-based Multimodal Topic Modeling

Automatically generated radiology reports often receive high scores from existing evaluation metrics but fail to earn clinicians’ trust. This gap reveals fundamental flaws in how current metrics assess the quality of generated reports. We rethink the design and evaluation of these metrics and propose a clinically grounded Meta-Evaluation Framework. We define clinically grounded criteria spanning clinical alignment and key metric capabilities, including discrimination, robustness, and monotonicity. Using a fine-grained dataset of ground truth and rewritten report pairs annotated with error types and clinical significance labels, we systematically evaluate widely used metrics and uncover their limitations, such as failing to distinguish clinically significant errors, over-penalizing harmless variations, or lacking consistency across error severity levels. Our framework and dataset offer guidance for building more clinically reliable evaluation methods.

ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment

Retrieval-augmented Generation (RAG) is powerful, but its effectiveness hinges on which retrievers we use and how. Different retrievers offer distinct, often complementary signals: BM25 captures lexical matches; dense retrievers, semantic similarity. Yet in practice, we typically fix a single retriever based on heuristics, which fails to generalize across diverse information needs. Can we dynamically select and integrate multiple retrievers for each individual query, without the need for manual selection? In our work, we validate this intuition with quantitative analysis and introduce a mixture of retrievers: a zero-shot, weighted combination of heterogeneous retrievers. Extensive experiments show that such mixtures are effective and efficient: Despite totaling just 0.8B parameters, this mixture outperforms every individual retriever and even larger 7B models—by +10.8% and +3.9% on average, respectively. Further analysis also shows that this mixture framework can help incorporate specialized non-oracle human information sources as retrievers to achieve good collaboration, with a 58.9% relative performance improvement over simulated humans alone.

Downloads

Next from EMNLP 2025

Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answering

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES