China

Small Language Models (SLMs) are becoming increasingly popular in specialized fields, such as industrial applications, due to their efficiency, lower computational requirements, and ability to be fine-tuned for domain-specific tasks, enabling accurate and cost-effective solutions. However, performing complex reasoning using SLMs in specialized fields such as Industry 4.0 remains challenging. In this paper, we propose a knowledge distillation framework for industrial asset health, which transfers reasoning capabilities via Chain-of-Thought (CoT) distillation from Large Language Models (LLMs) to smaller, more efficient models (SLMs). We discuss the advantages and the process of distilling LLMs using multi-choice question answering (MCQA) prompts to enhance reasoning and refine decision-making. We also perform in-context learning to verify the quality of the generated knowledge and benchmark the performance of fine-tuned SLMs with generated knowledge against widely used LLMs. The results show that the fine-tuned SLMs outperform the base models by a significant margin, narrowing the gap to their LLM counterparts.

EMNLP 2025

Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoring

fine tuning

reasoning

knowledge distillation

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*





<br>

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

Compositional generalization benchmarks seek to assess whether learning agents can successfully combine familiar concepts in novel ways. COGS (Kim & Linzen 2020, COGS, EMNLP) provides a suite of such tasks in the area of interpretive semantics (mapping sentences to logical forms). A noteworthy finding for COGS is that model performance varies widely across tasks. In this paper, we argue that these performance differences reflect deep properties of these tasks. We focus on two COGS tasks: an easy task (models are generally successful) and a hard task (no present-day models get any traction). Using both experiments and conceptual analysis, we argue that the easy task requires only a single distributional generalization that is well-supported by the training data, whereas the hard task involves a learning target that is ambiguous or even contradicted by the training data. We additionally argue that pretraining can disambiguate the hard task without compromising the goal of testing compositional generalization. Overall, our findings offer practical guidance to designers of compositional generalization benchmarks and also yield new insights into the nature of compositionality itself.

Distinguishing fair from unfair compositional generalization tasks

Autoregressive models excel in sequential modeling and have proven to be effective for vision- language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to suboptimal results. This work proposes a plug-and-play refinement module to enhance the complex spatial correspondence modeling within the generated visual sequence. This module operates as a post-pretraining step to jointly refine all generated tokens of autoregressive model, enhancing vision-language model- ing under a shared sequential prediction frame- work. By leveraging global context and relationship across the tokens, our method mitigates the error accumulation issue within the sequential generation. Experiments demonstrate that the proposed method improves the generation quality, enhancing the model’s ability to produce semantically consistent results.

Visual Self-Refinement for Autoregressive Models

Planning in modern LLM agents relies on the utilization of LLM as an internal world model, acquired during pretraining. However, existing agent designs lack a capacity to effectively assimilate new observations into dynamic updates of the world model. This inability means that reliance on the LLM’s static internal world model is progressively prone to misalignment with the underlying true state of the world, leading to the generation of divergent and erroneous plans. We introduce a hierarchical agent architecture, CoEx, in which hierarchical state abstraction allows LLM planning to co-evolve with a dynamically updated model of the world. CoEx plans and interacts with the world by using LLM reasoning to orchestrate dynamic plans consisting of subgoals, and its learning mechanism continuously incorporates these subgoal experiences into a persistent world model in the form of a neurosymbolic belief state, comprising textual inferences and code-based symbolic memory. We evaluate our agent across a diverse set of agent scenarios involving rich environments and complex tasks including ALFWorld, PDDL, and Jericho. Our experiments show that CoEx outperforms existing agent paradigms in planning and exploration.

CoEx – Co-evolving World-model and Exploration

We study the capabilities of large language models (LLMs) in detecting fine-grained anomalies in tabular data. Specifically, we examine: (1) how well LLMs can identify diverse anomaly types—including factual, logical, temporal, and value-based errors; (2) the impact of prompt design and prompting strategies; and (3) the effect of table structure and anomaly type on detection accuracy. To this end, we introduce TABARD, a new benchmark constructed by perturbing tables from WikiTQ, FeTaQA, Spider, and BEAVER. The dataset spans multiple domains and eight anomaly categories, including paired clean and corrupted tables. We evaluate LLMs using direct, indirect, and Chain-of-Thought (CoT) prompting. Our results reveal notable limitations in standard prompting, especially for complex reasoning tasks and longer tables. To overcome these issues, we propose a unified framework combining multi-step prompting, self-verification, and constraint-based rule execution. Our approach significantly improves precision and recall, offering a promising direction for robust and interpretable anomaly detection in tables.

TABARD: A Novel Benchmark for Tabular Anomaly Analysis, Reasoning and Detection

Design‐time safety guarantees for human-centered autonomous systems (HCAS) often break down in open-world deployment due to uncertain human interaction. In practice, HCAS must follow a user-personalized safety plan, with the human providing external inputs to handle out-of-distribution events. Open-world safety planning for HCAS demands modeling dynamical systems, exploring novel actions, and rapid replanning when plans are invalidated or dynamics shift. No single state-of-the-art planner meets all these needs. We introduce an LLM-based architecture that automatically generates personalized safety plans. By itself, the LLM fares poorly at producing safe usage plans, but coupling it with a safety verifier—which evaluates plan safety over the planning horizon and feeds back quality scores—enables the discovery of safe plans. Moreover, fine-tuning the LLM on personalized models inferred from open-world data further enhances plan quality. We validate our approach by generating safe usage plans for artificial pancreas systems in automated insulin delivery for Type 1 Diabetes patients.

Personalized open world plan generation for safety-critical human centered autonomous systems: A case study on Artificial Pancreas

We propose a large language model based reward decomposition framework for aligning dialogue agents using only a single session-level feedback signal. We leverage the reasoning capabilities of a frozen, pretrained large language model (LLM) to infer fine-grained local implicit rewards by decomposing global, session-level feedback. Our first text-only variant prompts the LLM to perform reward decomposition using only the dialogue transcript. The second multimodal variant incorporates additional behavioral cues, such as pitch, gaze, and facial affect, expressed as natural language descriptions. These inferred turn-level rewards are distilled into a lightweight reward model, which we utilize for RL-based fine-tuning for dialogue generation. We evaluate both text-only and multimodal variants against state-of-the-art reward decomposition methods and demonstrate notable improvements in human evaluations of conversation quality, suggesting that LLMs are strong reward decomposers that obviate the need for manual reward shaping and granular human feedback.

Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition

Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments. However, in multi-turn conversational environments like τ‑bench, these agents often struggle with consistent reasoning, adherence to domain-specific policies, and extracting correct information over a long horizon of tool-calls and conversation. To capture and mitigate these failures, we conduct a comprehensive manual analysis of the common errors occurring in the conversation trajectories. We then experiment with reformulations of inputs to the tool-calling agent for improvement in agent decision making. Finally, we propose the Input-Reformulation Multi-Agent (IRMA) framework, which automatically reformulates user queries augmented with relevant domain rules and tool suggestions for the tool-calling agent to focus on. The results show that IRMA significantly outperforms ReAct, Function Calling, and Self-Reflection by 16.1%, 12.7%, and 19.1%, respectively, in overall pass^5 scores. These findings highlight the superior reliability and consistency of IRMA compared to other methods in dynamic environments.

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ -bench

Protein-specific large language models (ProteinLLMs) are revolutionizing protein science by enabling more efficient protein structure prediction, function annotation, and design. While existing surveys focus on specific aspects or applications, this work provides the first comprehensive overview of ProteinLLMs, covering their architectures, training datasets, evaluation metrics, and diverse applications. Through a systematic analysis of over 100 articles, we propose a structured taxonomy of state-of-the-art ProteinLLMs, analyze how they leverage large-scale protein sequence data for improved accuracy, and explore their potential in advancing protein engineering and biomedical research. Additionally, we discuss key challenges and future directions, positioning ProteinLLMs as essential tools for scientific discovery in protein science. A GitHub repository and tutorial will be available upon publication.

Protein Large Language Models: A Comprehensive Survey

Using language models to scalably approximate human preferences on text quality (LLM-as-a-judge) has become a standard practice applicable to many tasks. A judgment is often extracted from the judge's textual output alone, typically with greedy decoding. However, LLM judges naturally provide distributions over judgment tokens, inviting a breadth of inference methods for extracting fine-grained preferences. We find that taking the mean of the judgment distribution consistently outperforms taking the mode (i.e. greedy decoding) in all evaluation settings (i.e. pointwise, pairwise, and listwise). We further explore novel methods of deriving preferences from judgment distributions, and find that methods incorporating risk aversion often improve performance. Lastly, we analyze LLM-as-a-judge paired with chain-of-thought (CoT) prompting, showing that CoT can collapse the spread of the judgment distribution, often harming performance. Our findings show that leveraging distributional output improves LLM-as-a-judge, as opposed to using the text interface alone.

Improving LLM-as-a-Judge Inference with the Judgment Distribution

Deep learning models trained on extensive Electronic Health Records (EHR) data have achieved high accuracy in diagnosis prediction, offering the potential to assist clinicians in decision-making and treatment planning. However, these models lack two crucial features that clinicians highly value: interpretability and interactivity. The ``black-box'' nature of these models makes it difficult for clinicians to understand the reasoning behind predictions, limiting their ability to make informed decisions. Additionally, the absence of interactive mechanisms prevents clinicians from incorporating their own knowledge and experience into the decision-making process. To address these limitations, we propose II-KEA, a knowledge-enhanced agent-driven causal discovery framework that integrates personalized knowledge databases and agentic LLMs. II-KEA enhances interpretability through explicit reasoning and causal analysis, while also improving interactivity by allowing clinicians to inject their knowledge and experience through customized knowledge bases and prompts. II-KEA is evaluated on both MIMIC-III and MIMIC-IV, demonstrating superior performance along with enhanced interpretability and interactivity, as evidenced by its strong results from extensive case studies.

Downloads

Next from EMNLP 2025

Distinguishing fair from unfair compositional generalization tasks

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES