Austria

Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to **Tool Overuse**, where models unnecessarily rely on external tools for tasks solvable with parametric knowledge, increasing computational overhead. Inspired by human metacognition, we introduce **SMART** (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent’s self-awareness to optimize task handling and reduce tool overuse. To support this paradigm, we introduce **SMART-ER**, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary. Through supervised training, we develop **SMARTAgent**, a family of models that dynamically balance parametric knowledge and tool use. Evaluations show that SMARTAgent reduces tool use by 24% while improving performance by over 37%, enabling 7B-scale models to match its 70B counterpart and GPT-4. Additionally, SMARTAgent generalizes to out-of-distribution test data like GSM8K and MINTQA, maintaining accuracy with just one-fifth the tool calls. These highlight the potential of strategic tool use to enhance reasoning, mitigate overuse, and bridge the gap between model size and performance, advancing intelligent and resource-efficient agent designs.

ACL 2025

SMART: Self-Aware Agent for Tool Overuse Mitigation

tool overuse

agent reasoning

llm agent

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

poster

### 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)

Recent advances in Large Language Models (LLMs) have led to remarkable improvements in language understanding and text generation. However, challenges remain in enhancing their performance for underrepresented languages, ensuring continual learning without catastrophic forgetting, and developing robust evaluation methodologies. This work addresses these issues by investigating the impact of Continued Pretraining (CPT) on multilingual models and proposing a comprehensive evaluation framework for LLMs. Our first contribution explores CPT strategies for languages with limited representation in multilingual models, focusing on Galician. We analyze how CPT with Galician corpora improves text generation while assessing the trade-offs between linguistic enrichment and task-solving capabilities. Our findings show that CPT with small, high-quality corpora and diverse instructions enhances both task performance and linguistic quality. Our second contribution is a structured evaluation framework based on distinguishing task-based and language-based assessments, leveraging existing and newly developed benchmarks for Galician. Additionally, we contribute new Galician LLMs, datasets for evaluation and instructions, and an evaluation framework.

Enhancing Multilingual Large Language Models: Continued Pretraining and Comprehensive Evaluation for Underrepresented Languages

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context faithfulness remain largely unexplored. In this study, we investigate the impact of memory strength and evidence presentation on LLMs' receptiveness to external evidence. We quantify the memory strength of LLMs by measuring the divergence in LLMs' responses to different paraphrases of the same question, which is not considered by previous works. We also generate evidence in various styles to examine LLMs' behavior. Our results show that for questions with high memory strength, LLMs are more likely to rely on internal memory. Furthermore, presenting paraphrased evidence significantly increases LLMs' receptiveness compared to simple repetition or adding details.

Investigating Context Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style

This paper delves into a novel backdoor attack scenario, aiming to uncover potential security risks associated with Multimodal Large Language Models (MLLMs) during multi-round open-ended conversations with users. In the practical use of MLLMs, users have full control over the interaction process with the model, such as using their own collected photos and posing arbitrary open-ended questions. Traditional backdoor attacks that rely on adding external triggers are less applicable. To this end, we introduce a new shadow-activated backdoor attacking paradigm in this paper, wherein attacks implicitly inject malicious content into the responses of MLLMs when the responses explicitly relate to the shadowed object, i.e., without any triggers. To facilitate the shadow-activated backdoor attack, we present a novel framework named BadMLLM to achieve the desired behaviors by constructing a poisoned dataset using GPT-4 Vision and implementing an attention-regularized tuning strategy to address the semantic discontinuity between the original response and the inserted promotion. Extensive experimental results conducted on five MLLMs, three objects, and two types of promotion slogans have demonstrated impressive performance in achieving both efficacy and utility goals, thereby highlighting the significant potential risks concealed within MLLMs.

Shadow-Activated Backdoor Attacks on Multimodal Large Language Models

Recent advancements in large language models (LLMs) have significantly improved software development automation, including bug localization, code synthesis, program repair, and test generation. However, most prior work on program repair focuses on isolated elements, such as classes or functions, neglecting their interdependencies, which limits repair accuracy. We present SynFix, a RelationGraph-based approach that integrates LLMs with structural search and synchronization techniques for coordinated program repair across codebases. SynFix constructs a \textbf{RelationGraph} to capture relationships among classes, functions, variables, and their interactions (e.g., imports, inheritance, dependencies). Each RelationGraph node includes detailed code descriptions to help LLMs understand root causes and retrieve relevant contexts. By analyzing one-hop nodes in the RelationGraph, SynFixensures repairs account for dependent updates across components. Patch validation is conducted using regression tests from the SWE-bench benchmark suite. Evaluated on SWE-bench datasets, SynFix resolves 52.33% of issues in \textbf{SWE-bench-lite} (300 GitHub issues), 55.8% in \textbf{SWE-bench-verified} (500 issues), and 29.86% in \textbf{SWE-bench-full} (2,294 issues), outperforming baselines such as Swe-Agent, Agentless and AutoCodeRover. The codebase is available at \url{https://anonymous.4open.science/r/AutoFix-EC86/}.

SynFix: Synchronous Repair for Codebase via RelationGraph

LLM-based multi-agent systems (MAS) have shown promise in tackling complex tasks. However, existing solutions often suffer from limited agent coordination and heavy reliance on predefined Standard Operating Procedures (SOPs), which demand extensive human input. To address these limitations, we propose MegaAgent, a large-scale autonomous LLM-based multi-agent system. MegaAgent generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication, and comprehensive system monitoring of agents. In evaluations, MegaAgent demonstrates exceptional performance, successfully developing a Gobang game within 800 seconds and scaling up to 590 agents in a national policy simulation to generate multi-domain policies. It significantly outperforms existing systems, such as MetaGPT, in both task completion efficiency and scalability. By eliminating the need for predefined SOPs, MegaAgent demonstrates exceptional scalability and autonomy, setting a foundation for advancing true autonomy in MAS. Code is available at https://github.com/Xtra-Computing/MegaAgent

MegaAgent: Dynamic Agent Coordination Without SOPs

As large language models (LLMs) become an important way of information access, there have been increasing concerns that LLMs may intensify the spread of unethical content, including implicit bias that hurts certain populations without explicit harmful words. In this paper, we conduct a rigorous evaluation of LLMs' implicit bias towards certain demographics by attacking them from a psychometric perspective to elicit agreements to biased viewpoints. Inspired by psychometric principles in cognitive and social psychology, we propose three attack approaches, i.e., Disguise, Deception, and Teaching. Incorporating the corresponding attack instructions, we built two benchmarks: (1) a bilingual dataset with biased statements covering four bias types (2.7K instances) for extensive comparative analysis, and (2) BUMBLE, a larger benchmark spanning nine common bias types (12.7K instances) for comprehensive evaluation. Extensive evaluation of popular commercial and open-source LLMs shows that our methods can elicit LLMs' inner bias more effectively than competitive baselines. Our attack methodology and benchmarks offer an effective means of assessing the ethical risks of LLMs, driving progress toward greater accountability in their development.

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective

Though current long-context large language models (LLMs) have demonstrated impressive capacities in answering various questions based on extensive text, the lack of citations in their responses makes user verification difficult, leading to concerns about their trustworthiness due to the potential hallucinations. In this work, we aim to enable long-context LLMs to generate responses with fine-grained sentence-level citations on the fly, thereby improving their faithfulness and verifiability. We first introduce LongBench-Cite, an automated benchmark for assessing current LLMs' performance in long-context question answering with citations (LQAC), revealing considerable room for improvement. To this end, we propose CoF (Coarse to Fine), a novel pipeline that utilizes off-the-shelf LLMs to automatically construct long-context QA instances with precise sentence-level citations, and leverage this pipeline to construct LongCite-45k, a large-scale SFT dataset for LQAC. Finally, we train LongCite-8B and LongCite-9B using the constructed dataset, successfully enabling the generation of accurate responses and fine-grained citations in one pass. The evaluation results on LongBench-Cite show that our trained models achieve state-of-the-art citation quality, surpassing advanced proprietary models including GPT-4o. We also discover that SFT with citation information can further improve the correctness of model responses compared to standard long-context SFT.

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-Context QA

Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning. While previous studies have extensively examined biases related to protected attributes such as race, the emergence and propagation of biases on socially contentious issues in multi-agent LLM interactions remain underexplored. This study explores how LLM agents shape public opinion through debates on five contentious topics. By simulating over 2,500 debates, we analyze how initially neutral agents, assigned a centrist disposition, adopt specific stances over time. Statistical analyses reveal significant group conformity mirroring human behavior; LLM agents tend to align with numerically dominant groups or more intelligent agents, exerting a greater influence. These findings underscore the crucial role of agent intelligence in shaping discourse and highlight the risks of bias amplification in online interactions. Our results emphasize the need for policy measures that promote diversity and transparency in LLM-generated discussions to mitigate the risks of bias propagation within anonymous online environments.

An Empirical Study of Group Conformity in Multi-Agent Systems

Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level uncertainty and hallucinations. We hypothesize that attention mechanisms inherently encode context utilization signals, supported by probing analysis. Based on these insights, we propose **Dynamic Attention-Guided Context Decoding (DAGCD)**, a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding. Experiments on open-book QA datasets demonstrate DAGCD’s effectiveness, yielding significant improvements in faithfulness and robustness while preserving computational efficiency.

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models

Despite remarkable advances in natural language processing, large Language Models (LLMs) are often prone to hallucination during inference due to the limited coverage of their training corpora. Although existing research has attempted to mitigate this limitation through Knowledge Graphs (KGs) enhancement, two core challenges remain: semantic gaps and redundant paths. Although semantic parsing can partially address these issues through precise graph pattern matching, it demonstrates limited generalizability when handling multi-hop reasoning scenarios. To this end, we propose the two-stage FIne-grainEd SemanTic pArsing (FIESTA) framework. In the offline stage, we construct a fine-grained mapping library through phrase-level segmentation. In the online stage, relevant clauses are retrieved and instantiated into local subgraphs, which are then fused into a global information subgraph. Experimental results on two KGQA datasets show the effectiveness ofFIESTA. Notably, it demonstrates a relative performance improvement of 18.5% over the SOTA method on the CWQ dataset.

Downloads

Next from ACL 2025

Enhancing Multilingual Large Language Models: Continued Pretraining and Comprehensive Evaluation for Underrepresented Languages

Similar lecture

Enhancing Tool Retrieval with Iterative Feedback from Large Language Models