Austria

The evaluation of large language models (LLMs) has traditionally relied on static benchmarks, a paradigm that poses two major limitations: (1) predefined test sets lack adaptability to diverse application domains, and (2) standardized evaluation protocols often fail to capture fine-grained assessments of domain-specific knowledge and contextual reasoning abilities. To overcome these challenges, we propose GuessArena, an adaptive evaluation framework grounded in adversarial game-based interactions. Inspired by the interactive structure of the Guess Who I Am? game, our framework seamlessly integrates dynamic domain knowledge modeling with progressive reasoning assessment to improve evaluation fidelity. Empirical studies across five vertical domains-finance, healthcare, manufacturing, information technology, and education-demonstrate that GuessArena effectively distinguishes LLMs in terms of domain knowledge coverage and reasoning chain completeness. Compared to conventional benchmarks, our method provides substantial advantages in interpretability, scalability, and scenario adaptability.

ACL 2025

GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning

domain knowledge evaluation

reasoning capabilities evaluation

adaptive evaluation framework

large language models

## 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)

The Theory of Multiple Intelligences underscores the hierarchical nature of cognitive capabilities. To advance Spatial Artificial Intelligence, we pioneer a psychometric framework defining five Basic Spatial Abilities (BSAs) in Visual Language Models (VLMs): Spatial Perception, Spatial Relation, Spatial Orientation, Mental Rotation, and Spatial Visualization. Benchmarking 13 mainstream VLMs through nine validated psychometric experiments reveals significant gaps versus humans, with three key findings: 1) VLMs mirror human hierarchies (strongest in 2D orientation, weakest in 3D rotation) with independent BSAs; 2) Many smaller models surpass larger counterparts, with Qwen leading and InternVL2 lagging; 3) Interventions like CoT and few-shot training show limits from architectural constraints, while ToT demonstrates the most effective enhancement. Identified barriers include weak geometry encoding and missing dynamic simulation. By linking Psychometrics to VLMs, we provide a comprehensive BSA evaluation benchmark, a methodological perspective for embodied AI development, and a cognitive science-informed roadmap for achieving human-like spatial intelligence.

Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics

Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle complex queries involving logical constructs such as negations, conjunctions, and disjunctions. In this paper, we propose a novel inference-time logical reasoning framework that explicitly incorporates logical reasoning into the retrieval process. Our method extracts logical reasoning structures from natural language queries and then composes the individual cosine similarity matching scores to formulate the final document scores. This approach enables the retrieval process to handle complex logical reasoning without compromising computational efficiency. Our results on both synthetic and real-world benchmarks demonstrate that the proposed method consistently outperforms traditional retrieval methods across different models and datasets, significantly improving retrieval performance for complex queries.

Enhancing Retrieval Systems with Inference-Time Logical Reasoning

Implicit Discourse Relation Recognition (abbr., IDRR) is a NLP task of classifying argument pairs into different types of semantic relations. Arguments contain subtexts, some of which are beneficial to the perception of semantic relations. However, subtexts are connotative. The neural IDRR model fails to be aware of them without being given pertinent prompts. In this paper, we leverage LLaMA to generate subtexts for argument pairs, and verify the effectiveness of subtext-based IDRR. We construct an IDRR baseline using the decoder-only backbone LLaMA, and enhance it with subtext-aware relation reasoning. A confidence-diagnosed dual-channel network is used for collaboration between in-subtext and out-of-subtext IDRR. We experiment on PDTB-2.0 and PDTB-3.0 for both the main-level and secondary-level relation taxonomies. The test results show that our approach yields substantial improvements compared to the baseline, and achieves higher $F$1-scores on both benchmarks than the previous decoder-only IDRR models. We make the source codes and data publicly available.

Using Subtext to Enhance Generative IDRR

The goal of conversational product search (CPS) is to develop an intelligent, chat-based shopping assistant that can directly interact with customers to understand shopping intents, ask clarification questions, and find relevant products. However, training such assistants is hindered mainly due to the lack of reliable and large-scale datasets. Prior human-annotated CPS datasets are extremely small in size and lack integration with real-world product search systems. We propose a novel approach, TRACER, which leverages large language models (LLMs) to generate realistic and natural conversations for different shopping domains. TRACER's novelty lies in grounding the generation to dialogue plans, which are product search trajectories predicted from a decision tree model, that guarantees relevant product discovery in the shortest number of search conditions. We also release the first target-oriented CPS dataset Wizard of Shopping (WoS), containing highly natural and coherent conversations (3.6k) from three shopping domains. Finally, we demonstrate the quality and effectiveness of WoS via human evaluations and downstream tasks.

Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branching

Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeable performance degradation, while Mixture-of-Experts (MoE) models require extensive computational resources. In this paper, we propose L0-MoE, a lightweight MoE approach using L0-regularization to accelerate dense LLMs nearly without performance loss. Our method introduces a cluster confusion matrix for domain-aware dataset curation and applies dynamic batching for efficient training. Experiments show that L0-MoE achieves up to 2.5x speedup over dense models while maintaining competitive performance, outperforming existing LLM acceleration baselines.

Accelerating Dense LLMs via L0-regularized Mixture-of-Experts

This paper introduces MadaKV, a modality-adaptive key-value (KV) cache eviction strategy designed to enhance the efficiency of multimodal large language models (MLLMs) in long-context inference. In multimodal scenarios, attention heads exhibit varying preferences for different modalities, resulting in significant disparities in modality importance across attention heads. Traditional KV cache eviction methods, which are tailored for unimodal settings, fail to capture modality-specific information, thereby yielding suboptimal performance. MadaKV addresses these challenges through two key components: modality preference adaptation and hierarchical compression compensation. By dynamically sensing modality information within attention heads and adaptively retaining critical tokens, MadaKV achieves substantial reductions in KV cache memory footprint and model inference decoding latency (1.3 to 1.5 times improvement) while maintaining high accuracy across various multimodal long-context tasks. Extensive experiments on representative MLLMs and the MileBench benchmark demonstrate the effectiveness of MadaKV compared to existing KV cache eviction methods.

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference

Efficient retrieval of pinpointed information from case law is crucial for legal professionals but challenging due to the length and complexity of legal judgments. Existing works mostly often focus on retrieving entire cases rather than precise, paragraph-level information. Moreover, multilingual legal practice necessitates cross-lingual retrieval, most works have been limited to monolingual settings. To address these gaps, we introduce LexCLiPR, a cross-lingual dataset for paragraph-level retrieval from European Court of Human Rights (ECtHR) judgments, leveraging multilingual case law guides and distant supervision to curate our dataset. We evaluate retrieval models in a zero-shot setting, revealing the limitations of pre-trained multilingual models for cross-lingual tasks in low-resource languages and the importance of retrieval based post-training strategies. In fine-tuning settings, we observe that two-tower models excel in cross-lingual retrieval, while siamese architectures are better suited for monolingual tasks. Fine-tuning multilingual models on native language queries improves performance but struggles to generalize to unseen legal concepts, highlighting the need for robust strategies to address topical distribution shifts in the legal queries.

LexCLiPR: Cross-Lingual Paragraph Retrieval from Legal Judgments

The financial industry faces a substantial workload in verifying document images. Existing methods based on visual features struggle to identify fraudulent document images due to the lack of visual clues on the tampering region. This paper proposes CSIAD (Cross-Sample Image Anomaly Detection) by leveraging LLMs to identify logical inconsistencies in similar images. This novel framework accurately detects forged images with slight tampering traces and explains anomaly detection results. Furthermore, we introduce CrossCred, a new benchmark of real-world fraudulent images with fine-grained manual annotations. Experiments demonstrate that CSIAD outperforms state-of-the-art image fraud detection methods by 79.6% (F1) on CrossCred and deployed industrial solutions by 21.7% (F1) on business data. The benchmark is available at https://github.com/XMUDM/CSIAD.

Innovative Image Fraud Detection with Cross-Sample Anomaly Analysis: The Power of LLMs

Large language models hold promise for addressing medical challenges, such as medical diagnosis reasoning, research knowledge acquisition, clinical decision-making, and consumer health inquiry support. However, they often generate hallucinations due to limited medical knowledge. Incorporating external knowledge is therefore critical, which necessitates multi-source knowledge acquisition. We address this challenge by framing it as a source planning problem, which is to formulate context-appropriate queries tailored to the attributes of diverse sources. Existing approaches either overlook source planning or fail to achieve it effectively due to misalignment between the model's expectation of the sources and their actual content. To bridge this gap, we present MedOmniKB, a repository comprising multigenre and multi-structured medical knowledge sources. Leveraging these sources, we propose the Source Planning Optimisation method, which enhances multi-source utilisation. Our approach involves enabling an expert model to explore and evaluate potential plans while training a smaller model to learn source alignment. Experimental results demonstrate that our method substantially improves multi-source planning performance, enabling the optimised small model to achieve state-of-the-art results in leveraging diverse medical knowledge sources.

Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications

This paper addresses the gap in predicting turn-taking and backchannel actions in human-machine conversations using multi-modal signals (linguistic, acoustic, and visual). To overcome the limitation of existing datasets, we propose an automatic data collection pipeline that allows us to collect and annotate over 210 hours of human conversation videos. From this, we construct a Multi-Modal Face-to-Face (MM-F2F) human conversation dataset, including over 1.5M words and corresponding turn-taking and backchannel annotations from approximately 20M frames. Additionally, we present an end-to-end framework that predicts the probability of turn-taking and backchannel actions from multi-modal signals. The proposed model emphasizes the interrelation between modalities and supports any combination of text, audio, and video inputs, making it adaptable to a variety of realistic scenarios. Our experiments show that our approach achieves state-of-the-art performance on turn-taking and backchannel prediction tasks, achieving a 10% increase in F1-score on turn-taking and a 33% increase on backchannel prediction. Our dataset and code are publicly available online to ease of subsequent research.

Downloads

Next from ACL 2025

Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics

Similar lecture

Assessing LLM Reasoning Steps via Principal Knowledge Grounding