China

Equipped with the capability to call functions, modern LLM agents can leverage external tools for addressing a range of tasks unattainable through language skills alone. However, the effective execution of these tools relies heavily not just on the advanced capabilities of LLM agents but also on precise user instructions, which often cannot be ensured in the real world. To evaluate the performance of LLM agents tool-use under imperfect instructions, we meticulously examine the real-world instructions queried from users, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench. We find that due to the next-token prediction training objective, LLM agents tend to arbitrarily generate the missed argument, which may lead to hallucinations and risks. To address this issue, we propose a novel framework, Ask-when-Needed, which prompts LLM agents to ask questions to users whenever they encounter obstacles due to unclear instructions. Moreover, to reduce the manual labor involved in user-LLM interaction and assess LLM agents&#39; performance in tool utilization from both accuracy and efficiency perspectives, we design an automated evaluation tool named ToolEvaluator. Our experiments demonstrate that the Ask-when-Needed significantly outperforms existing frameworks for tool learning in the Noisy ToolBench. We will release all related code and datasets to support future research.

EMNLP 2025

Learning to Ask: When LLM Agents Meet Unclear Instruction

code understanding

application

code generation

robustness

### 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**. 

ACL 2025

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

Equipped with the capability to call functions, modern LLM agents can leverage external tools for addressing a range of tasks unattainable through language skills alone. However, the effective execution of these tools relies heavily not just on the advanced capabilities of LLM agents but also on precise user instructions, which often cannot be ensured in the real world. To evaluate the performance of LLM agents tool-use under imperfect instructions, we meticulously examine the real-world instructions queried from users, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench. We find that due to the next-token prediction training objective, LLM agents tend to arbitrarily generate the missed argument, which may lead to hallucinations and risks. To address this issue, we propose a novel framework, Ask-when-Needed, which prompts LLM agents to ask questions to users whenever they encounter obstacles due to unclear instructions. Moreover, to reduce the manual labor involved in user-LLM interaction and assess LLM agents' performance in tool utilization from both accuracy and efficiency perspectives, we design an automated evaluation tool named ToolEvaluator. Our experiments demonstrate that the Ask-when-Needed significantly outperforms existing frameworks for tool learning in the Noisy ToolBench. We will release all related code and datasets to support future research.

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

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

Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document retrieval, achieving notable improvements in QA performance, but underperform on complex, multi-hop QA resulting from the sparse rewards from global signal only. To address this gap in existing research, we introduce StepSearch, a framework for search LLMs that trained with step-wise proximal policy optimization method. It consists of richer and more detailed intermediate search rewards and token-level process supervision based on information gain and redundancy penalties to better guide each search step. We constructed a fine-grained question-answering dataset containing sub-question-level search trajectories based on open source datasets through a set of data pipeline method. On standard multi-hop QA benchmarks, it significantly outperforms global-reward baselines, achieving 11.2% and 4.2% absolute improvements for 3B and 7B models over various search with RL baselines using only 19k training data, demonstrating the effectiveness of fine-grained, stepwise supervision in optimizing deep search LLMs.

StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization

Recent advances in large language models (LLMs) have opened new possibilities for table-based tasks. However, most existing methods remain confined to single-table settings, limiting their applicability to real-world databases composed of multiple interrelated tables. In multi-table scenarios, LLMs face two key challenges: reasoning over relational structures beyond sequential text, and handling the input length limitations imposed by large-scale table concatenation. To address these issues, we propose Guided Relational Integration for multiple Tables (GRIT), a lightweight method that converts relational schemas into LLM-friendly textual representations. GRIT employs hashing-based techniques to efficiently infer primary–foreign key relationships and constructs prompts that explicitly encode relevant join paths and question-relevant columns. When applied to off-the-shelf LLMs, GRIT consistently improves table-column retrieval performance across diverse multi-table benchmarks while significantly reducing memory and computational overhead.

GRIT: Guided Relational Integration for Efficient Multi-Table Understanding

Multimodal neural machine translation (MNMT), has received increasing attention due to its widespread applications in various fields such as cross-border e-commerce and cross-border social media platforms. The task which aims to integrate other modalities, such as the visual modality, with textual data to enhance translation performance, has recently received a lot of attention. We survey the major milestones in MNMT research, discussing key challenges and promising research directions for advancing MNMT.

Multimodal Neural Machine Translation: A Survey of the State of the Art

Retrieval Augmented Generation (RAG) frameworks can improve the factual accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge. However, these systems are susceptible to adversarial attacks that manipulate the retrieval process by introducing documents that are adversarial yet semantically similar to the query. Notably, while these adversarial documents resemble the query, they exhibit weak similarity to benign documents in the retrieval set. Thus, we propose a simple yet effective **G**raph-based **R**eranking against **A**dversarial **D**ocument **A**ttacks (GRADA) framework aiming at preserving retrieval quality while significantly reducing the success of adversaries. Our study evaluates the effectiveness of our approach through experiments conducted on six LLMs: GPT-3.5-Turbo, GPT-4o, Llama3.1-8b-Instruct, Llama3.1-70b-Instruct, Qwen2.5-7b-Instruct and Qwen2.5-14b-Instruct. We use three datasets to assess performance, with results from the Natural Questions dataset demonstrating up to an 80% reduction in attack success rates while maintaining minimal loss in accuracy.

GRADA: Graph-based Reranking against Adversarial Documents Attack

Video-to-audio synthesis, which generates synchronized audio for visual content, critically enhances viewer immersion and narrative coherence in film and interactive media. However, video-to-audio dubbing for long-form content remains an unsolved challenge due to dynamic semantic shifts, audio diversity and the absence of dedicated datasets. While existing methods excel in short videos, they falter in long scenarios (e.g., movies) due to fragmented synthesis and inadequate cross-scene consistency. We propose LVAS-Agent, a multi-agent framework that offers a coordinated, multi-component approach to long-video audio generation. Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, audio design and audio synthesis. To enable systematic evaluation, we introduce LVAS-Bench, the first benchmark with 207 professionally curated long videos spanning diverse scenarios. Experiments show that our method outperforms state-of-the-art V2A models in overall audio synthesis quality.

Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesis

Conventional retrieval-augmented generation(RAG) systems employ rigid retrieval strategies that create: (1) knowledge blind spots across domain boundaries, (2) reasoning fragmentation when processing interdependent concepts, and (3) contradictions from conflicting evidence sources. Motivated by these limitations, we introduce PathwiseRAG, which addresses these challenges through: intent-aware strategy selection to eliminate blind spots, dynamic reasoning networks that capture sub-problem interdependencies to overcome fragmentation, and parallel path exploration with adaptive refinement to resolve conflicts. The framework models query intent across semantic and reasoning dimensions, constructs a directed acyclic graph of interconnected sub-problems, and explores multiple reasoning trajectories while continuously adapting to emerging evidence. Evaluation across challenging benchmarks demonstrates significant improvements over state-of-the-art RAG systems, with average accuracy gains of 4.9% and up to 6.9% on complex queries, establishing a new paradigm for knowledge-intensive reasoning by transforming static retrieval into dynamic, multi-dimensional exploration.

PathwiseRAG: Multi-Dimensional Exploration and Integration Framework

In an era where misinformation spreads freely, fact-checking (FC) plays a crucial role in verifying claims and promoting reliable information. While automated fact-checking (AFC) has advanced significantly, existing systems remain vulnerable to adversarial attacks that manipulate or generate claims, evidence, or claim-evidence pairs. These attacks can distort the truth, mislead decision-makers, and ultimately undermine the reliability of FC models. Despite growing research interest in adversarial attacks against AFC systems, a comprehensive, holistic overview of key challenges remains lacking. These challenges include understanding attack strategies, assessing the resilience of current models, and identifying ways to enhance robustness. This survey provides the first in-depth review of adversarial attacks targeting FC, categorizing existing attack methodologies and evaluating their impact on AFC systems. Additionally, we examine recent advancements in adversary-aware defenses and highlight open research questions that require further exploration. Our findings underscore the urgent need for resilient FC frameworks capable of withstanding adversarial manipulations in pursuit of preserving high verification accuracy.

Adversarial Attacks Against Automated Fact-Checking: A Survey

Multi-hop question answering faces substantial challenges due to data sparsity, which increases the likelihood of language models learning spurious patterns. To address this issue, prior research has focused on diversifying question generation through content planning and varied expression. However, these approaches often emphasize generating simple questions and neglect the integration of essential knowledge, such as relevant sentences within documents. This paper introduces the **Knowledge Composition Sampling (KCS)**, an innovative framework designed to expand the diversity of generated multi-hop questions by sampling varied knowledge compositions within a given context. KCS models the knowledge composition selection as a sentence-level conditional prediction task and utilizes a probabilistic contrastive loss to predict the next most relevant piece of knowledge. During inference, we employ a stochastic decoding strategy to effectively balance accuracy and diversity. Compared to competitive baselines, our KCS improves the average accuracy of knowledge composition selection by 3.9%, and its application for data augmentation yields improvements on HotpotQA and 2WikiMultihopQA.

KCS: Diversify Multi-hop Question Generation with Knowledge Composition Sampling

Entity alignment (EA), critical for knowledge graph (KG) integration, identifies equivalent entities across different KGs. Traditional methods often face challenges in semantic understanding and scalability. The rise of language models (LMs), particularly large language models (LLMs), has provided powerful new strategies. This paper systematically reviews LM-driven EA methods, proposing a novel taxonomy that categorizes methods in three key stages: data preparation, feature embedding, and alignment. We further summarize key benchmarks, evaluation metrics, and discuss future directions. This paper aims to provide researchers and practitioners with a clear and comprehensive understanding of how language models reshape the field of entity alignment.

How do Language Models Reshape Entity Alignment? A Survey of LM-Driven EA Methods: Advances, Benchmarks, and Future

Molecule and text representation learning has gained increasing interest due to its potential for enhancing the understanding of chemical information. However, existing models often struggle to capture subtle differences between molecules and their descriptions, as they lack the ability to learn fine-grained alignments between molecular substructures and chemical phrases. To address this limitation, we introduce MolBridge, a novel molecule–text learning framework based on substructure-aware alignments. Specifically, we augment the original molecule–description pairs with additional alignment signals derived from molecular substructures and chemical phrases. To effectively learn from these enriched alignments, MolBridge employs substructure-aware contrastive learning, coupled with a self-refinement mechanism that filters out noisy alignment signals. Experimental results show that MolBridge effectively captures fine-grained correspondences and outperforms state-of-the-art baselines on a wide range of molecular benchmarks, highlighting the significance of substructure-aware alignment in molecule-text learning.

Downloads

Next from EMNLP 2025

StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization

Similar lecture

A Joint Optimization Framework for Enhancing Efficiency of Tool Utilization in LLM Agents