China

Debugging is a critical aspect of LLM&#39;s coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understanding of algorithmic logic. Recent advancements in large language models (LLMs) have shifted attention toward leveraging natural language reasoning to enhance code-related tasks. However, two fundamental questions remain unanswered: What type of natural language format is most effective for debugging tasks? And what specific benefits does natural language reasoning bring to the debugging process? In this paper, we introduce NL-DEBUGGING, a novel framework that employs natural language as an intermediate representation to improve code debugging. By debugging at a natural language level, we demonstrate that NL-DEBUGGING outperforms traditional debugging methods and enables a broader modification space through direct refinement guided by execution feedback. Our findings highlight the potential of natural language reasoning to advance automated code debugging and address complex programming challenges.

EMNLP 2025

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging

code debugging

natural language reasoning

large language models

### 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)

Debugging is a critical aspect of LLM's coding ability. Early debugging efforts primarily focused on code-level analysis, which often falls short when addressing complex programming errors that require a deeper understanding of algorithmic logic. Recent advancements in large language models (LLMs) have shifted attention toward leveraging natural language reasoning to enhance code-related tasks. However, two fundamental questions remain unanswered: What type of natural language format is most effective for debugging tasks? And what specific benefits does natural language reasoning bring to the debugging process? In this paper, we introduce NL-DEBUGGING, a novel framework that employs natural language as an intermediate representation to improve code debugging. By debugging at a natural language level, we demonstrate that NL-DEBUGGING outperforms traditional debugging methods and enables a broader modification space through direct refinement guided by execution feedback. Our findings highlight the potential of natural language reasoning to advance automated code debugging and address complex programming challenges.

technical paper

## 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.

Large language models (LLMs) are capable of generating coherent summaries from very long contexts given a user query, and extracting and citing evidence spans helps improve the trustworthiness of these summaries. Whereas previous work has focused on evidence citation with fixed levels of granularity (e.g. sentence, paragraph, document, etc.), we propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case. We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be "lost-in-the-middle". To help models perform this task, we create the Summaries with Unstructured Evidence Text dataset (SUnsET), a synthetic dataset generated using a novel pipeline, which can be used as training supervision for unstructured evidence summarization. We demonstrate across 5 LLMs and 4 datasets spanning human written, synthetic, single, and multi-document settings that LLMs adapted with SUnsET generate more relevant and factually consistent evidence with their summaries, extract evidence from more diverse locations in their context, and can generate more relevant and consistent summaries than baselines with no fine-tuning and fixed granularity evidence. We release SUnsET and our generation code to the public (https://anonymous.4open.science/r/sunset-BD72/README.md).

Unstructured Evidence Attribution for Long Context Query Focused Summarization

This paper focuses on Dialogue Aspect-based Sentiment Quadruple (DiaASQ) analysis, aiming to extract structured quadruples from multi-turn conversations. Applying Large Language Models (LLMs) for this specific task presents two primary challenges: the accurate extraction of multiple elements and the understanding of complex dialogue reply structure. To tackle these issues, we propose a novel LLM-based multi-task approach, named textbfTask-textbfaware textbfContrastive textbfMixture textbfof textbfExperts (textbfTaCoMoE), to tackle the DiaASQ task by integrating expert-level contrastive loss within task-oriented mixture of experts layer. TaCoMoE minimizes the distance between the representations of the same expert in the semantic space while maximizing the distance between the representations of different experts to efficiently learn representations of different task samples. Additionally, we design a Graph-Centric Dialogue Structuring strategy for representing dialogue reply structure and perform non-opinion utterances detection to enhance the performance of quadruple extraction. Extensive experiments are conducted on the DiaASQ dataset, demonstrating that our method significantly outperforms existing parameter-efficient fine-tuning techniques in terms of both accuracy and computational efficiency. The code is available at https://anonymous.4open.science/r/TaCoMoE-08B4.

Task-aware Contrastive Mixture of Experts for Quadruple Extraction in Conversations with Code-like Replies and Non-opinion Detection

Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL) approaches, while the correctness of intermediate think-and-search steps is usually neglected. To address this issue, we design a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. Grounded on this, we propose **Le**arning to **T**hink-and-**S**earch (**LeTS**), a novel framework that hybridizes stepwise process reward and outcome-based reward to current RL methods for RAG. Extensive experiments demonstrate the generalization and inference efficiency of **LeTS** across various RAG benchmarks. In addition, these results reveal the potential of process- and outcome-level reward hybridization in boosting LLMs' reasoning ability via RL under other scenarios.

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

Large language models demonstrate strong problem-solving abilities through reasoning techniques such as chain-of-thought prompting and reflection. However, it remains unclear whether these reasoning capabilities extend to a form of social intelligence: making effective decisions in cooperative contexts. We examine this question using economic games that simulate social dilemmas. First, we apply chain-of-thought and reflection prompting to GPT-4o in a Public Goods Game. We then evaluate multiple off-the-shelf models across six cooperation and punishment games, comparing those with and without explicit reasoning mechanisms. We find that reasoning models consistently reduce cooperation and norm enforcement, favoring individual rationality. In repeated interactions, groups with more reasoning agents exhibit lower collective gains. These behaviors mirror human patterns of "spontaneous giving and calculated greed." Our findings underscore the need for LLM architectures that incorporate social intelligence alongside reasoning, to help address—rather than reinforce—the challenges of collective action.

Spontaneous Giving and Calculated Greed in Language Models

The rapid development of large language models (LLMs) gives rise to ethical concerns about their performance, while opening new avenues for developing toxic language detection techniques. However, LLMs’ unethical output and their capability of detecting toxicity have primarily been tested on language data that do not demand complex meaning inference, such as the biased associations of ‘he’ with programmer and ‘she’ with household. Nowadays toxic language adopts a much more creative range of implicit forms, thanks to advanced censorship. In this study, we collect authentic toxic interactions that evade online censorship and that are verified by human annotators as inference-intensive. To evaluate and improve LLMs' reasoning of the authentic implicit toxic language, we propose a new prompting method, Pragmatic Inference Chain (PIC), drawn on interdisciplinary findings from cognitive science and linguistics. The PIC prompting significantly improves the success rate of GPT-4o, Llama-3.1-70B-Instruct, DeepSeek-v2.5, and DeepSeek-v3 in identifying implicit toxic language, compared to five baseline prompts, such as CoT and rule-based baselines. In addition, it also facilitates the models to produce more explicit and coherent reasoning processes, hence can potentially be generalized to other inference-intensive tasks, e.g., understanding humour and metaphors.

Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language

Stance detection aims to identify the viewpoint (favor, against, or neutral) expressed in text towards a specific target. Recent studies on zero-shot and few-shot stance detection focus primarily on learning generalized representations from explicit targets. However, these methods often neglect **implicit yet semantically important targets** and fail to sufficiently **exploit fine-grained contextual cues**, limiting model performance in nuanced scenarios. To overcome these limitations, we propose a novel two-stage framework: First, a data augmentation framework named **Hierarchical Collaborative Target Augmentation** (HCTA) employs Large Language Models (LLMs) to identify and annotate implicit targets via Chain-of-Thought (CoT) prompting and multi-model voting, significantly enriching training data with latent semantic relations. Second, we introduce **FiCAN, a Fine-grained Context-aware Attention Network**, integrating a joint text-target encoding and a sparse cross-attention mechanism to selectively capture critical fine-grained contextual clues. Experiments on the VAST benchmark dataset demonstrate that our approach achieves state-of-the-art results, confirming the effectiveness of implicit target augmentation and fine-grained contextual modeling.

LLM-Driven Implicit Target Augmentation and Fine-Grained Contextual Modeling for Zero-Shot and Few-Shot Stance Detection

Discovering customer intentions in dialogue conversations is crucial for automated service agents. However, existing intent clustering methods often fail to align with human perceptions due to a heavy reliance on embedding distance metrics and a tendency to overlook underlying semantic structures. This paper proposes an **LLM-in-the-loop (LLM-ITL)** intent clustering framework, integrating the semantic understanding capabilities of LLMs into conventional clustering algorithms. Specifically, this paper (1) investigates the effectiveness of fine-tuned LLMs in semantic coherence evaluation and intent cluster naming, achieving over 95\% accuracy aligned with human judgments; (2) designs an LLM-ITL framework that facilitates the iterative discovery of coherent intent clusters and the optimal number of clusters; and (3) proposes context-aware techniques tailored for customer service dialogue. As existing English benchmarks offer limited semantic diversity and intent groups, we introduce a comprehensive Chinese dialogue intent dataset, comprising over 100k real customer service calls and 1,507 human-annotated intent clusters. The proposed approaches significantly outperform LLM-guided baselines, achieving notable enhancements in clustering quality and lower computational cost. Combined with several best practices, our findings highlight the potential of LLM-in-the-loop techniques for scalable and human-aligned intent clustering.

Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues

The empathy dialogue system requires understanding emotions and their underlying causes. However, existing datasets mainly focus on emotion labels, while cause annotations are added post hoc through costly and subjective manual processes. This leads to three limitations: subjective bias in cause labels, weak rationality due to ambiguous cause-emotion relationships, and high annotation costs that hinder scalability. To address these challenges, we propose ECC (Emotion-Cause Conversation Dataset), a scalable dataset with 2.4K dialogues, which is also the first dialogue dataset where conversations and their emotion-cause labels are automatically generated synergistically during creation. We create an automatic extension framework EC-DD for ECC that utilizes knowledge and large language models (LLMs) to automatically generate conversations, and train a causality-aware empathetic response model CAER on this dataset. Experimental results show that ECC can achieve comparable or even superior performance to artificially constructed empathy dialogue datasets. All code, data, and models will be publicly released to advance empathetic AI research.

ECC: An Emotion-Cause Conversation Dataset for Empathy Response

The emergence of Multimodal Large Reasoning Models (MLRMs) has enabled sophisticated visual reasoning capabilities by integrating reinforcement learning and Chain-of-Thought (CoT) supervision. However, while these enhanced reasoning capabilities improve performance, they also introduce new and underexplored safety risks. In this work, we systematically investigate the security implications of advanced visual reasoning in MLRMs. Our analysis reveals a fundamental trade-off: as visual reasoning improves, models become more vulnerable to jailbreak attacks. Motivated by this critical finding, we introduce VisCRA (Visual Chain Reasoning Attack), a novel jailbreak framework that exploits the visual reasoning chains to bypass safety mechanisms. VisCRA combines targeted visual attention masking with a two-stage reasoning induction strategy to precisely control harmful outputs. Extensive experiments demonstrate VisCRA's significant effectiveness, achieving high attack success rates on leading closed-source MLRMs: 76.48% on Gemini 2.0 Flash Thinking, 68.56% on QvQ-Max, and 56.60% on GPT-4o. Our findings highlight a critical insight: the very capability that empowers MLRMs — their visual reasoning — can also serve as an attack vector, posing significant security risks. Warning: This paper contains unsafe examples.

VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models

This paper investigates how LLMs encode inputs with typos. We hypothesize that specific neurons and attention heads recognize typos and fix them internally using local and global contexts. We introduce a method to identify typo neurons and typo heads that work actively when inputs contain typos. Our experimental results suggest the following: 1) LLMs can fix typos with local contexts when the typo neurons in either the early or late layers are activated, even if those in the other are not. 2) Typo neurons in the middle layers are the core of typo-fixing with global contexts. 3) Typo heads fix typos by widely considering the context not focusing on specific tokens. 4) Typo neurons and typo heads work not only for typo-fixing but also for understanding general contexts.

Downloads

Next from EMNLP 2025

Unstructured Evidence Attribution for Long Context Query Focused Summarization

Similar lecture

Revisit Self-Debugging with Self-Generated Tests for Code Generation