Austria

Scientific language models drive research innovation but require extensive fine-tuning on large datasets. This work enhances such models by improving their inference and evaluation capabilities with minimal or no additional training. Focusing on molecule caption generation, we explore post-training synergies between alignment fine-tuning and model merging in a cross-modal setup. We reveal intriguing insights into the behaviour and suitability of such methods while significantly surpassing state-of-the-art models. Moreover, we propose a novel atomic-level evaluation method leveraging off-the-shelf Natural Language Inference (NLI) models for use in the unseen chemical domain. Our experiments demonstrate that our evaluation operates at the right level of granularity, effectively handling multiple content units and subsentence reasoning, while widely adopted NLI methods consistently misalign with assessment criteria.

ACL 2025

Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation

low-resource training

chemical llms

rlhf

## 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." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

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

technical paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Despite the remarkable success of attention-based large language models (LLMs), the precise interaction mechanisms between attention heads remain poorly understood. In contrast to prevalent methods that focus on individual head contributions, we rigorously analyze the intricate interplay among attention heads through a novel framework based on the Harsanyi dividend, a concept from cooperative game theory. Our analysis reveals that significant positive Harsanyi dividends are sparsely distributed across head combinations, indicating that most heads do not contribute cooperatively. Moreover, certain head combinations exhibit negative dividends, indicating implicit competitive relationships. To further optimize the interactions among attention heads, we propose a training-free Game-theoretic Attention Calibration (GAC) method. Specifically, GAC selectively retains heads demonstrating significant cooperative gains and applies fine-grained distributional adjustments to the remaining heads. Comprehensive experiments across 17 benchmarks demonstrate the effectiveness of our proposed GAC and its superior generalization capabilities across diverse model families, scales, and modalities. Crucially, the discovered interaction phenomena offer a path toward a deeper understanding of the behaviors of LLMs.

Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective

The difficulty intrinsic to a given example, rooted in its inherent ambiguity, is a key yet often overlooked factor in evaluating neural NLP models. We investigate the interplay and divergence among various metrics for assessing intrinsic difficulty, including annotator dissensus, training dynamics, and model confidence. Through a comprehensive analysis using 29 models on three datasets, we reveal that while correlations exist among these metrics, their relationships are neither linear nor monotonic. By disentangling these dimensions of uncertainty, we aim to refine our understanding of data complexity and its implications for evaluating and improving NLP models.

Your Model is Overconfident, and Other Lies We Tell Ourselves

With the continuous advancement in the performance of open-source large language models (LLMs), their inference services have attracted a substantial user base by offering quality comparable to closed-source models at a significantly lower cost. However, it has also given rise to trust issues regarding model consistency between users and third-party service providers. Specifically, service providers can effortlessly degrade a model's parameter scale or precision for more margin profits, and although users may perceptibly experience differences in text quality, they often lack a reliable method for concrete monitoring. To address this problem, we propose a paradigm for model consistency monitoring on the user side. It constructs metrics based on the logits produced by LLMs to differentiate sequences generated by degraded models. Furthermore, by leveraging model offloading techniques, we demonstrate that the proposed method is implementable on consumer-grade devices. Metric evaluations conducted on three widely used LLMs series (OPT, Llama 3.1 and Qwen 2.5) along with system prototype efficiency tests on a consumer device (RTX 3080 TI) confirm both the effectiveness and feasibility of the proposed approach.

User-side Model Consistency Monitoring for Open Source Large Language Models Inference Services

Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior. A major challenge in student simulation is modeling the diverse learning patterns of students at various cognitive levels. However, current LLMs, typically trained as "helpful assistants", target at generating perfect responses. As a result, they struggle to simulate students with diverse cognitive abilities, as they often produce overly advanced answers, missing the natural imperfections that characterize student learning and resulting in unrealistic simulations. To address this issue, we propose a training-free framework for student simulation. We begin by constructing a cognitive prototype for each student using a knowledge graph, which captures their understanding of concepts from past learning records. This prototype is then mapped to new tasks to predict student performance. Next, we simulate student solutions based on these predictions and iteratively refine them using a beam search method to better replicate realistic mistakes. To validate our approach, we construct the Student_100 dataset, consisting of 100 students working on Python programming and 5,000 learning records. Experimental results show that our method consistently outperforms baseline models, achieving 100% improvement in simulation accuracy and realism.

Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents

Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various solutions for knowledge updating, they often struggle with sequential editing scenarios and harm the general capabilities of the model, thereby significantly hampering their practical applicability.
This paper proposes a two-stage framework combining robust supervised fine-tuning (R-SFT) with model merging for knowledge editing. Our method first fine-tunes the LLM to internalize new knowledge fully, then merges the fine-tuned model with the original foundation model to preserve newly acquired knowledge and general capabilities. 
Experimental results demonstrate that our approach significantly outperforms existing methods in sequential editing while better preserving the original performance of the model, all without requiring any architectural changes. Code is available at [Applied-Machine-Learning-Lab/MM4KE](https://github.com/Applied-Machine-Learning-Lab/MM4KE).

Model Merging for Knowledge Editing

As AI chatbots become ubiquitous, voice interaction presents a compelling way to enable rapid, high-bandwidth communication for both semantic and social signals. This has driven research into Large Audio Models (LAMs) to power voice-native experiences. However, aligning LAM development with user goals requires a clear understanding of user needs and preferences to establish reliable progress metrics. This study addresses these challenges by introducing an interactive approach to evaluate LAMs and collecting 7,500 LAM interactions from 484 participants. Through topic modeling of user queries, we identify primary use cases for audio interfaces. We then analyze user preference rankings and qualitative feedback to determine which models best align with user needs. Finally, we evaluate how static benchmarks predict interactive performance - our analysis reveals no individual benchmark strongly correlates with interactive results ($\tau \leq 0.33$ for all benchmarks). While combining multiple coarse-grained features yields modest predictive power ($R^2$=$0.30$), only two out of twenty datasets on spoken question answering and age prediction show significantly positive correlations. This suggests a clear need to develop LAM evaluations that better correlate with user preferences.

Mind the Gap: Static and Interactive Evaluations of Large Audio Models

Argument mining has garnered increasing attention over the years, with the recent advancement of Large Language Models (LLMs) further propelling this trend. However, current argument relations remain relatively simplistic and foundational, struggling to capture the full scope of argument information. To address this limitation, we propose a systematic framework comprising 14 fine-grained relation types from the perspectives of vertical argument relations and horizontal discourse relations, thereby capturing the intricate interplay between argument components for a thorough understanding of argument structure. On this basis, we conducted extensive experiments on three tasks: argument component prediction, relation prediction, and automated essay grading. Additionally, we explored the impact of writing quality on argument component prediction and relation prediction, as well as the connections between discourse relations and argumentative features. The findings highlight the importance of fine-grained argumentative annotations for argumentative writing assessment and encourage multi-dimensional argument analysis.

Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method

The research on classical Chinese event extraction trends to directly graft the complex modeling from English or modern Chinese works, neglecting the utilization of the unique characteristic of this language. We argue that, compared with grafting the sophisticated methods from other languages, focusing on classical Chinese's inimitable source of __Ancient Literature__ could provide us with extra and comprehensive semantics in event extraction. Motivated by this, we propose a Literary Vision-Language Model (VLM) for classical Chinese event extraction, integrating with literature annotations, historical background and character glyph to capture the inner- and outer-context information from the sequence. Extensive experiments build a new state-of-the-art performance in the GuwenEE, CHED datasets, which underscores the effectiveness of our proposed VLM, and more importantly, these unique features can be obtained precisely at nearly zero cost.

Revisiting Classical Chinese Event Extraction with Ancient Literature Information

Lexicalized parsing, which associates constituent nodes with lexical heads, has historically played a crucial role in constituency parsing by bridging constituency and dependency structures. Nevertheless, with the advent of neural networks, lexicalized structures have generally been neglected in favor of unlexicalized, span-based methods. In this paper, we revisit lexicalized parsing and propose a novel latent lexicalization framework that dynamically infers lexical heads during training without relying on predefined head-finding rules. Our method enables the model to learn lexical dependencies directly from data, offering greater adaptability across languages and datasets. Experiments on multiple treebanks demonstrate state-of-the-art or comparable performance. We also analyze the learned dependency structures, headword preferences, and linguistic biases.

Dynamic Head Selection for Neural Lexicalized Constituency Parsing

Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks, thereby predominantly reflecting Western-centric concepts. In this paper, we introduce "INJONGO" - a multicultural, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains, including banking, travel, home, and dining. Through extensive experiments, we benchmark fine-tuning multilingual transformer models and prompting large language models (LLMs), and show the advantage of leveraging African-cultural utterances over Western-centric utterances for improving cross-lingual transfer from the English language. Experimental results reveal that current LLMs struggle with the slot-filling task, with GPT-4o achieving an average performance of 26 F1. In contrast, intent detection performance is notably better, with an average accuracy of 70.6%, though it still falls short of fine-tuning baselines. When compared to the English language, GPT-4o and fine-tuning baselines perform similarly on intent detection, achieving an accuracy of approximately 81%. Our findings suggest that LLMs performance is still behind for many low-resource African languages, and more work is needed to further improve their downstream performance.

Downloads

Next from ACL 2025

Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective

Similar lecture

Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction