Austria

Large language models (LLMs) have been widely deployed as autonomous agents capable of following user instructions and making decisions in real-world applications. Previous studies have made notable progress in benchmarking the instruction following capabilities of LLMs in general domains, with a primary focus on their inherent commonsense knowledge. Recently, LLMs have been increasingly deployed as domain-oriented agents, which rely on domain-oriented guidelines that may conflict with their commonsense knowledge. These guidelines exhibit two key characteristics: they consist of a wide range of domain-oriented rules and are subject to frequent updates. Despite these challenges, the absence of comprehensive benchmarks for evaluating the domain-oriented guideline following capabilities of LLMs presents a significant obstacle to their effective assessment and further development. In this paper, we introduce GuideBench, a comprehensive benchmark designed to evaluate guideline following performance of LLMs. GuideBench evaluates LLMs on three critical aspects: (i) adherence to diverse rules, (ii) robustness to rule updates, and (iii) alignment with human preferences. Experimental results on a range of LLMs indicate substantial opportunities for improving their ability to follow domain-oriented guidelines. Data and code are available at Anonymous.

ACL 2025

GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents

llm benchmark

llm agents

llm reasoning

large language models

instruction following

## 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)

Mainstream issue-resolving frameworks predominantly rely on commercial models, leading to high costs and privacy concerns. Existing training approaches for issue resolving struggle with poor generalization and fail to fully leverage open-source development resources. We propose **S**ubtask-**o**riented **R**einforced **F**ine-**T**uning (**SoRFT**), a novel training approach to enhance the issue resolving capability of LLMs. We decomposes issue resolving into structured subtasks: file localization, function localization, line localization, and code edit generation. SoRFT consists of two training stages: (1) **rejection-sampled supervised fine-tuning**, Chain of Thought (CoT) data is filtered using ground-truth before fine-tuning the LLM, and (2) **rule-based reinforcement learning**, which leverages PPO with ground-truth based rewards. We evaluate the SoRFT-trained model on SWE-Bench Verified and SWE-Bench Lite, achieving state-of-the-art (SOTA) performance among open-source models (e.g., resolve 21.4% issues on SWE-Bench Verified with SoRFT-Qwen-7B). The experimental results demonstrate that SoRFT significantly enhances issue-resolving performance, improves model generalization, and provides a cost-efficient alternative to commercial models.

SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning

Automatic exploit generation (AEG) refers to the automatic discovery and exploitation of vulnerabilities against unknown targets. Traditional AEG often targets a single type of vulnerability and still relies on templates built from expert experience. To achieve intelligent exploit generation, we establish a comprehensive benchmark using Binary Exploitation (pwn) challenges in Capture the Flag (CTF) competitions and investigate the capabilities of Large Language Models (LLMs) in AEG based on the benchmark. To improve the performance of AEG, we propose PwnGPT, an LLM-based automatic exploit generation framework that automatically solves pwn challenges. The structural design of PwnGPT is divided into three main components: analysis, generation, and verification modules. With the help of a modular approach and structured problem inputs, PwnGPT can solve challenges that LLMs cannot directly solve. We evaluate PwnGPT on our benchmark and analyze the outputs of each module. Experimental results show that our framework is highly autonomous and capable of addressing various challenges. Compared to direct input LLMs, PwnGPT increases the completion rate of exploit on our benchmark from 26.3\% to 57.9\% with the OpenAI o1-preview model and from 21.1\% to 36.8\% with the GPT-4o model.

PwnGPT: Automatic Exploit Generation Based on Large Language Models

While data synthesis and distillation are promising strategies to enhance small language models, current approaches heavily rely on Large Language Models (LLMs), which suffer from high computational costs, environmental inefficiency, and potential biases inherited from monolithic architectures. In contrast, smaller LMs are more accessible and sustainable, but their individual capabilities often fall short in generating high-quality, diverse, and reliable data. Inspired by collaborative human processes (e.g., peer review), we propose a multiple small LMs involved framework, GRA, that aggregates specialized roles across small LMs to iterative refinement and quality control typically achieved by a single large LM. 
In this collaborative framework, multiple small LMs assume distinct roles—Generator, Reviewer, and Adjudicator—to simulate a peer-review-inspired data synthesis pipeline. The Generator proposes initial data samples, the Reviewer critiques their quality and diversity, and the Adjudicator resolves conflicts to finalize the output. By decomposing the synthesis process into specialized sub-tasks, collaborative small LMs can achieve data-level parity with distillation from large LMs. Through experiments across multiple benchmarks, we demonstrate that GRA-produced data matches or exceeds the quality of single large LM outputs, e.g., Qwen-2.5-72B-Instruct. Our results challenge the necessity of monolithic large models for high-quality data synthesis, advocating instead for strategic coordination of smaller agents.

A Strategic Coordination Framework of Small LMs Matches Large LMs in Data Synthesis

We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholar queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academic queries to assess PaSa performance in more realistic scenarios. Despite being trained on synthetic data, PaSa significantly outperforms existing baselines on RealScholarQuery, including Google, Google Scholar, Google with GPT-4o for paraphrased queries, ChatGPT (search-enabled GPT-4o), GPT-o1, and PaSa-GPT-4o (PaSa implemented by prompting GPT-4o). Notably, PaSa-7B surpasses the best Google-based baseline, Google with GPT-4o, by 37.78% in recall@20 and 39.90% in recall@50, and exceeds PaSa-GPT-4o by 30.36% in recall and 4.25% in precision. Model, datasets, and code are available at https://github.com/bytedance/pasa.
Demo: https://pasa-agent.ai

PaSa: An LLM Agent for Comprehensive Academic Paper Search

Recent advances in Large Language Models (LLMs) have yielded impressive successes on many language tasks. However, efficient processing of long contexts using LLMs remains a significant challenge. We introduce **EpMAN** -- a method for processing long contexts in an episodic memory module while holistically attending to semantically-relevant context chunks. Output from episodic attention is then used to reweigh the decoder's self-attention to the stored KV cache of the context during training and generation. When an LLM decoder is trained using **EpMAN**, its performance on multiple challenging single-hop long-context recall and question-answering benchmarks is found to be stronger and more robust across the range from 16k to 256k tokens than baseline decoders trained with self-attention, and popular retrieval-augmented generation frameworks.

EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts

Multi-modal Large Language Models (MLLMs) integrating images, text, and speech can provide farmers with accurate diagnoses and treatment of pests and diseases, enhancing agricultural efficiency and sustainability. However, existing benchmarks lack comprehensive evaluations, particularly in multi-level reasoning, making it challenging to identify model limitations. To address this issue, we introduce Agri-CM$^3$, an expert-validated benchmark assessing MLLMs’ understanding and reasoning in agricultural management. It includes 3,939 images and 15,901 multi-level multiple-choice questions with detailed explanations. Evaluations of 45 MLLMs reveal significant gaps. Even GPT-4o achieves only 63.64\% accuracy, falling short in fine-grained reasoning tasks. Analysis across three reasoning levels and seven compositional abilities highlights key challenges in accuracy and cognitive understanding. Our study provides insights for advancing MLLMs in agricultural management, driving their development and application. Code and data are available at \url{https://github.com/HIT-Kwoo/Agri-CM3}.

Agri-CM3: A Chinese Massive Multi-modal, Multi-level Benchmark for Agricultural Understanding and Reasoning

With the impressive reasoning and text generation capabilities of large language models (LLMs), methods leveraging multiple LLMs to debate each other have garnered increasing attention. However, existing debate-based approaches remain limited in effectiveness in structured and detailed domains represented by code generation due to several reasons: 1) Reliance on different instances of the same LLM for debate, neglecting the potential benefits of integrating diverse models with varied internal knowledge for more comprehensive code generation, 2) under-utilization of test cases, and 3) reliance on third-party LLM moderators for result consolidation and decision-making, probably introducing hallucinations and judgment errors. To address these challenges, we propose DebateCoder to collect intelligence of LLMs via test case-driven debate for code generation. In DebateCoder, test cases serve as a medium for models to analyze code and identify bugs, while opposing models generate test cases to challenge each other's code during the debate process. These test cases, along with their execution results, are elaborately leveraged to refine and enhance the code through a novel contrastive analysis process. Furthermore, DebateCoder leverages test case outcomes to assess code quality and determine convergence criteria. Unlike previous approaches, DebateCoder emphasizes the collaborative improvement of both models through competitive debate and interactive analysis. Abundant experimental results on two datasets demonstrate the effectiveness of DebateCoder.

DebateCoder: Towards Collective Intelligence of LLMs via Test Case Driven LLM Debate for Code Generation

Modern zero-shot text-to-speech (TTS) systems, despite using extensive pre-training, often struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis, leading to intelligibility issues. To address these limitations, this paper leverages preference alignment techniques, which enable targeted construction of out-of-pretraining-distribution data to enhance performance. We introduce a new dataset, named the Intelligibility Preference Speech Dataset (INTP), and extend the Direct Preference Optimization (DPO) framework to accommodate diverse TTS architectures. After INTP alignment, in addition to intelligibility, we observe overall improvements including naturalness, similarity, and audio quality for multiple TTS models across diverse domains. Based on that, we also verify the weak-to-strong generalization ability of INTP for more intelligible models such as CosyVoice 2 and Ints. Moreover, we showcase the potential for further improvements through iterative alignment based on Ints. Audio samples are available at https://intalign.github.io/.

Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment

In knowledge graph embedding, leveraging relation specific entity transformation has markedly enhanced performance. However, the consistency of embedding differences before and after transformation remains unaddressed, risking the loss of valuable inductive bias inherent in the embeddings. This inconsistency stems from two problems. First, transformation representations are specified for relations in a disconnected manner, allowing dissimilar transformations and corresponding entity embeddings for similar relations. Second, a generalized plug-in approach as a SFBR (Semantic Filter Based on Relations) disrupts this consistency through excessive concentration of entity embeddings under entity-based regularization, generating indistinguishable score distributions among relations. In this paper, we introduce a plug-in KGE method, Relation-Semantics Consistent Filter (RSCF). Its entity transformation has three features for enhancing semantic consistency: 1) shared affine transformation of relation embeddings across all relations, 2) rooted entity transformation that adds an entity embedding to its change represented by the transformed vector, and 3) normalization of the change to prevent scale reduction. To amplify the advantages of consistency that preserve semantics on embeddings, RSCF adds relation transformation and prediction modules for enhancing the semantics. In knowledge graph completion tasks with distance-based and tensor decomposition models, RSCF significantly outperforms state-of-the-art KGE methods, showing robustness across all relations and their frequencies.

RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge Graph

Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD) paradigm. However, current approaches face a critical dilemma: TOD systems are often trained on a limited set of target APIs, requiring new data to maintain their quality when interfacing with new services, while LAs are not trained to maintain user intent over multi-turn conversations. Because both robust multi-turn management and advanced function calling are crucial for effective conversational agents, we evaluate these skills on three popular benchmarks: MultiWOZ 2.4 (TOD), BFCL V3 (LA), and API-Bank (LA)—and our analyses reveal that specialized approaches excel in one domain but underperform in the other. To bridge this chasm, we introduce **CoALM** (**C**onversational **A**gentic **L**anguage **M**odel), a unified approach that integrates both conversational and agentic capabilities. We created **CoALM-IT**, a carefully constructed multi-task dataset that interleave multi-turn ReAct reasoning with complex API usage. Using CoALM-IT, we train three models **CoALM 8B**, **CoALM 70B**, and **CoALM 405B**, which outperform top domain-specific models, including GPT-4o, across all three benchmarks. This demonstrates the feasibility of a single model approach for both TOD and LA, setting a new standard for conversational agents.

Downloads

Next from ACL 2025

SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning

Similar lecture

Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection