Austria

The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, assigning a score to the input based on scoring rubrics. Existing methods for fine-tuning LLM-as-a-judge use cross-entropy (CE) loss, which neglects the numeric nature of score prediction. Recent work addresses numerical prediction limitations of LLM fine-tuning through regression-aware fine-tuning but does not consider chain-of-thought (CoT) reasoning for score prediction. In this paper, we introduce TRACT (Two-stage Regression-Aware fine-tuning with CoT), which combines CoT reasoning with regression-aware training. TRACT uses a two-stage process: first, it fine-tunes the seed LLM to generate CoTs, which serve as the training data for the second stage; next, it uses these self-generated CoTs to retrain the seed LLM. The fine-tuning objective of TRACT applies CE loss for CoT reasoning and regression-aware loss for the score. Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods. Extensive ablation studies validate the effectiveness of each component in TRACT.

ACL 2025

TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge

automatic evaluation of datasets

evaluation methodologies

llm-as-a-judge

evaluation

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

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)

Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models (LLMs). However, progress has been hindered by a lack of reliable evaluation datasets. To address this, we present ToolHop, a dataset comprising 995 user queries and 3,912 associated tools, specifically designed for rigorous evaluation of multi-hop tool use. ToolHop ensures diverse queries, meaningful interdependencies, locally executable tools, detailed feedback, and verifiable answers through a novel query-driven data construction approach that includes tool creation, document refinement, and code generation. We evaluate 14 LLMs across five model families (i.e., LLaMA3.1, Qwen2.5, Gemini1.5, Claude3.5, and GPT), uncovering significant challenges in handling multi-hop tool-use scenarios. The leading model, GPT-4o, achieves an accuracy of 49.04%, underscoring substantial room for improvement. Further analysis reveals variations in tool-use strategies for various families, offering actionable insights to guide the development of more effective approaches. Code and data can be found in https://huggingface.co/datasets/bytedance-research/ToolHop.

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use

Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip LLMs with the ability to process long inputs. However, it still remains an open challenge to measure the quality of long-context training data. To address this issue, we propose a Long-context data selection framework with Attention-based Dependency Measurement (LADM), which can efficiently identify high-quality long-context data from a large-scale, multi-domain pre-training corpus. LADM leverages the retrieval capabilities of the attention mechanism to capture contextual dependencies, ensuring a comprehensive quality measurement of long-context data. Experimental results show that our LADM framework significantly boosts the performance of LLMs on multiple long-context tasks with only 1B tokens for continual training.

LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs

Adapting large language models (LLMs) to diverse cultural values is a challenging task, as existing LLMs often reflect the values of specific groups by default, and potentially cause harm to others. In this paper, we present CLCA, a novel framework for enhancing LLM alignment with cultural values based on cultural learning. The framework leverages simulated social interactions to generate conversations in which LLMs engage in role-playing within culturally adapted social scenarios, capturing implicit cultural norms for model fine-tuning. CLCA improves cultural value alignment across various model architectures measured using World Value Survey data, demonstrating the effectiveness of our proposed approach. Our results provide early evidence that understanding intent and social interactions can enhance cultural value adaptation in LLMs, highlighting the promise of training approaches based on cultural learning.

Cultural Learning-Based Culture Adaptation of Language Models

Subtitles play a crucial role in improving the accessibility of the vast amount of audiovisual content available on the Internet, allowing audiences worldwide to comprehend and engage with this content in various languages. Automatic subtitling (AS) systems are essential for alleviating the substantial workload of human transcribers and translators. However, existing AS corpora and the primary metric SubER focus on European languages. This paper introduces A-TASC, an Asian TED-based automatic subtitling corpus derived from English TED Talks, comprising nearly 800 hours of audio segments, aligned English transcripts, and subtitles in Chinese, Japanese, Korean, and Vietnamese. We then present SacreSubER, a modification of SubER, to enable the reliable evaluation of subtitle quality for languages without explicit word boundaries. Experimental results, using both end-to-end systems and pipeline approaches built on strong ASR and LLM components, validate the quality of the proposed corpus and reveal differences in AS performance between European and Asian languages. The code to build our corpus is released.

A-TASC: Asian TED-Based Automatic Subtitling Corpus

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse generating unsafe content. We introduce a novel approach, \textbf{De}coupled \textbf{R}efusal \textbf{T}r\textbf{a}ining (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position, significantly enhancing their safety capabilities. DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation (MLE) with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence. Our empirical evaluation, conducted using LLaMA3 and Mistral model families across six attack scenarios, demonstrates that our method not only improves model safety without compromising performance but also surpasses baseline methods in defending against attacks.

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Peer review is a cornerstone of quality control in scientific publishing. With the increasing workload, the unintended use of `quick' heuristics, referred to as \emph{lazy thinking}, has emerged as a recurring issue compromising review quality. Automated methods to detect such heuristics can help improve the peer-reviewing process. However, there is limited NLP research on this issue, and no real-world dataset exists to support the development of detection tools. This work introduces $\textsc{LazyReview}$, a dataset of peer-review sentences annotated with fine-grained \emph{lazy thinking} categories. Our analysis reveals that Large Language Models (LLMs) struggle to detect these instances in a zero-shot setting. However, instruction-based fine-tuning on our dataset significantly boosts performance by 10-20 performance points, highlighting the importance of high-quality training data. Furthermore, a controlled experiment demonstrates that reviews revised with \emph{lazy thinking} feedback are more comprehensive and actionable than those written without such feedback. We will release our dataset and the enhanced guidelines that can be used to train junior reviewers in the community.

LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews

LLMs are aligned to follow input instructions by learning which of two responses users prefer for a prompt. However, such preference data do not convey *why* users prefer responses that are chosen or rejected, so LLMs trained on these datasets cannot tailor responses to varied user needs. To surface these parameters of personalization, we apply *abductive reasoning* to preference data, inferring needs and interests of users, i.e., personas, that may prefer either response. We test this idea in two steps: **Persona Inference (PI)**—abductively inferring personas of users who prefer chosen or rejected outputs—and **Persona Tailoring (PT)**—training models to tailor outputs to personas from PI. We show: 1) LLMs infer personas accurately explaining why different users may prefer *both* chosen or rejected outputs; 2) Training on preference data augmented with PI personas via PT boosts personalization and generalizes to supporting user-written personas; and 3) Rejected response personas form harder personalization evaluations, showing PT better aids users with uncommon preferences versus typical alignment methods. We argue for an abductive view of preferences for personalization, asking not only which response is better but when, why, and for whom.

Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas

The rise of social media has amplified the spread of fake news, now further complicated by large language models (LLMs) like ChatGPT, which ease the generation of highly convincing, error-free misinformation, making it increasingly challenging for the public to discern truth from falsehood. Traditional fake news detection methods relying on linguistic cues have also become less effective. Moreover, current detectors primarily focus on binary classification and English texts, often overlooking the distinction between machine-generated true vs. fake news and the detection in low-resource languages. To this end, we updated the detection schema to include machine-generated news focusing on Urdu. We further propose a conjoint detection strategy to improve the accuracy and robustness. Experiments show its effectiveness across four datasets in various settings.

Detection of Human and Machine-Authored Fake News in Urdu

Text-attributed graphs (TAGs) are prevalent in various real-world applications, including academic networks, e-commerce platforms, and social networks. Effective learning on TAGs requires leveraging both textual node features and structural graph information. While language models (LMs) excel at processing text and graph neural networks (GNNs) effectively capture relational structures, their direct integration is computationally prohibitive due to the high cost of text and graph representation learning. Existing approaches address this challenge by adopting a two-step pipeline where LMs generate fixed node embeddings, which are then used for GNN training. However, this method neglects the interaction between textual and structural information, leading to suboptimal learning outcomes. To overcome these limitations, we propose SKETCH (Semantic Knowledge and Structure Enrichment), a novel framework that decouples node aggregation from graph convolution and integrates it into the text representation learning process. SKETCH enhances TAG learning by incorporating two key aggregation mechanisms: (1) Semantic aggregation, which retrieves semantically relevant node texts for contextual enrichment, and (2) Structural aggregation, which propagates textual features beyond immediate neighbors to capture broader graph relationships. Extensive experiments demonstrate that SKETCH outperforms state-of-the-art TAG learning methods while requiring fewer computational resources. By enabling a more efficient and effective fusion of textual and structural information, SKETCH provides new insights into TAG problems and offers a practical solution for real applications.

Taming Language Models for Text-attributed Graph Learning with Decoupled Aggregation

Large vision-language models (LVLMs) have made substantial progress in integrating large language models (LLMs) with visual inputs, enabling advanced multimodal reasoning. Despite their success, a persistent challenge is hallucination—where generated text fails to accurately reflect visual content—undermining both accuracy and reliability. Existing methods focus on alignment training or decoding refinements but primarily address symptoms at the generation stage without probing the underlying causes. In this work, we investigate the internal mechanisms driving hallucination in LVLMs, with an emphasis on the multi-head attention module. Specifically, we introduce Vision-aware Head Divergence (VHD), a metric that quantifies the sensitivity of attention head outputs to visual context. Based on this, our findings reveal the presence of vision-aware attention heads that are more attuned to visual information; however, the model's overreliance on its prior language patterns is closely related to hallucinations. Building on these insights, we propose Vision-aware Head Reinforcement (VHR), a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads. Extensive experiments demonstrate that our method achieves superior performance compared to state-of-the-art approaches in mitigating hallucinations, while maintaining high efficiency with negligible additional time overhead. The code is available at https://github.com/jinghan1he/VHR.

Downloads

Next from ACL 2025

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use

Similar lecture

On the Impact of Fine-Tuning on Chain-of-Thought Reasoning