Austria

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.

ACL 2025

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

large audio models

speech processing

evaluation

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

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

Counterfactual data augmentation, which generates minimally edited tokens to alter labels, has become a key approach to improving model robustness in natural language processing (NLP). It is usually implemented by first identifying the causal terms and then modifying these terms to create counterfactual candidates. The emergence of large language models (LLMs) has effectively facilitated the task of counterfactual data augmentation. However, existing LLM-based approaches still face some challenges in 1) accurately extracting the task-specific causal terms, and 2) the quality of LLM-generated counterfacts. To address the issues, we propose a dually self-improved counterfactual data augmentation method using LLM for the Natural Language Inference (NLI) task. On the one hand, we design a self-improved strategy employing the attention distribution of the task model to identify the task-specific causal terms, which is lightweight and task-specific. On the other hand, a second self-improved strategy based on direct preference optimization is utilized to refine LLM-generated counterfacts, achieving high-quality counterfacts. Finally, a balanced loss preventing over-emphasis on augmented data is proposed to retrain the task model on the fusion of existing data and generated counterfacts. Extensive experiments on NLI benchmarks demonstrate the effectiveness of our proposed method in generating high-quality counterfacts for improving task performance.

Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model

Topic modeling aims to discover the distribution of topics within a corpus. The advanced comprehension and generative capabilities of large language models (LLMs) have introduced new avenues for topic modeling, particularly by prompting LLMs to generate topics and refine them by merging similar ones. However, this approach necessitates that LLMs generate topics with consistent granularity, thus relying on the exceptional instruction-following capabilities of closed-source LLMs (such as GPT-4) or requiring additional training. Moreover, merging based only on topic words and neglecting the fine-grained semantics within documents might fail to fully uncover the underlying topic structure. In this work, we propose a semi-supervised topic modeling method, LiSA, that combines LLMs with clustering to improve topic generation and distribution. Specifically, we begin with prompting LLMs to generate a candidate topic word for each document, thereby constructing a topic-level semantic space. To further utilize the mutual complementarity between them, we first cluster documents and candidate topic words, and then establish a mapping from document to topic in the LLM-guided assignment stage. Subsequently, we introduce a collaborative enhancement strategy to align the two semantic spaces and establish a better topic distribution. Experimental results demonstrate that LiSA outperforms state-of-the-art methods that utilize GPT-4 on topic alignment, and exhibits competitive performance compared to Neural Topic Models on topic quality. The codes are available at https://github.com/ljh986/LiSA.

LLM-Guided Semantic-Aware Clustering for Topic Modeling

Proactive questioning is essential in psychological conversations as it helps uncover deeper issues and unspoken concerns. Current psychological LLMs are constrained by passive response mechanisms, limiting their capacity to deploy proactive strategies for psychological counseling. To bridge this gap, we first develop the ProPsyC (Proactive Psychological Conversation) dataset, a multi-turn conversation dataset with interpretive labels including strategy decision logic and reaction attribution. Based on ProPsyC, we propose PsyAdvisor by supervised fine-tuning, a plug-and-play proactive questioning strategy planner that empowers psychological LLMs to initiate well-timed questioning through strategic prompting. Experimental results demonstrate that psychological LLMs integrated with PsyAdvisor substantially improve proactive questioning capacity, conversation depth, and response quality.
Furthermore, PsyAdvisor shows promising potential in assisting novice counselors by providing strategy recommendations. This study provides new optimization directions for psychological conversation systems and offers valuable insights for future research on proactive questioning mechanisms in psychological LLMs.

PsyAdvisor: A Plug-and-Play Strategy Advice Planner with Proactive Questioning in Psychological Conversations

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often exhibit a specific cultural bias, neglecting the values and linguistic diversity of low-resource regions. This cultural bias not only undermines universal equality but also risks reinforcing stereotypes and perpetuating discrimination. To address this, we propose CulFiT, a novel culturally-aware training paradigm that leverages multilingual data and fine-grained reward modeling to enhance cultural sensitivity and inclusivity. Our approach synthesizes diverse cultural-related questions, constructs critique data in multiple culturally relevant languages, and employs fine-grained rewards to decompose cultural texts into verifiable knowledge units for interpretable evaluation. We also introduce GlobalOpinionQA, a multilingual open-ended question-answering dataset designed to evaluate culturally-aware responses in a global context. Extensive experiments on three existing benchmarks and our GlobalOpinionQA demonstrate that CulFiT achieves state-of-the-art open-source model performance in cultural alignment and general reasoning.

CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis

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

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

Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment