Austria

Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks, yet the intricacies of their problem-solving mechanisms in system 2 tasks are not sufficiently explored. Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation and compressing the explored knowledge into System 1 process. In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges: (1) the complex hidden reasoning processes and (2) the heterogeneous data distributions that complicate the exploration and training of robust LLM solvers. To tackle these issues, we propose a novel BDC framework that explores insightful System 2 knowledge of LLMs using a MC-Tree-Of-Agents algorithm with mutual \textbf{B}oosting, \textbf{D}isentangles the heterogeneous training data for composable LoRA-experts, and obtain \textbf{C}ustomized problem solver for each data instance with an input-aware hypernetwork to weight over the LoRA-experts, offering effectiveness, flexibility, and robustness. This framework leverages multiple LLMs through mutual verification and boosting, integrated into a Monte-Carlo Tree Search process enhanced by reflection-based pruning and refinement. Additionally, we introduce the DisenLora algorithm, which clusters heterogeneous data to fine-tune LLMs into composable Lora experts, enabling the adaptive generation of customized problem solvers through an input-aware hypernetwork. Our contributions include the identification of critical challenges in existing methodologies, the development of the MC-Tree-of-Agents algorithm for insightful data collection, and the creation of a robust and flexible solution for code generation. This work lays the groundwork for advancing LLM capabilities in complex reasoning tasks, offering a novel System2-to-System1 solution.

ACL 2025

Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation

system2-to-system1

code generation

large language models

## 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*

EMNLP 2025

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

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)

Generating knowledge-intensive and comprehensive long texts, such as encyclopedia articles, remains significant challenges for Large Language Models. It requires not only the precise integration of facts but also the maintenance of thematic coherence throughout the article. Existing methods, such as multi-agent discussion, often struggle with issues like hallucinations, topic incoherence, and significant latency. To address these challenges, we propose RAPID, an efficient **R**etrieval-**A**ugmented long text generation framework with writing **P**lanning and **I**nformation **D**iscovery. RAPID consists of three main modules: (1) Retrieval-augmented preliminary outline generation to reduce hallucinations, (2) Attribute-constrained search for efficient information discovery, (3) Plan-guided article generation for enhanced coherence. Extensive experiments on our newly compiled benchmark dataset, FreshWiki-2024, demonstrate that RAPID significantly outperforms state-of-the-art methods across a wide range of evaluation metrics (\eg long-text generation, outline quality, latency, etc). Our work provides a robust and efficient solution to the challenges of automated long-text generation.

RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery

LLM providers typically offer multiple LLM tiers, varying in performance and price. As NLP tasks become more complex and modularized, selecting the suitable LLM tier for each subtask is a key challenge to balance between cost and performance. To address the problem, we introduce LLM Automatic Transmission (LLM-AT) framework that automatically selects LLM tiers without training. LLM-AT consists of Starter, Generator, and Judge. The starter selects the initial LLM tier expected to solve the given question, the generator produces a response using the LLM of the selected tier, and the judge evaluates the validity of the response. If the response is invalid, LLM-AT iteratively upgrades to a higher-tier model, generates a new response, and re-evaluates until a valid response is obtained. Additionally, we propose accuracy estimator, which enables the suitable initial LLM tier selection without training. Given an input question, accuracy estimator estimates the expected accuracy of each LLM tier by computing the valid response rate across top-k similar queries from past inference records. Experiments demonstrate that LLM-AT achieves superior performance while reducing costs, making it a practical solution for real-world applications.

Automatic Transmission for LLM Tiers: Optimizing Cost and Accuracy in Large Language Models

Multimodal entity linking (MEL), a task aimed at linking mentions within multimodal contexts to their corresponding entities in a knowledge base (KB), has attracted much attention due to its wide applications in recent years. However, existing MEL methods often rely on mention words as retrieval cues, which limits their ability to effectively utilize information from both images and text. This reliance causes MEL to struggle with accurately retrieving entities in certain scenarios, especially when the focus is on image objects or mention words are missing from the text. To solve these issues, we introduce a Visual Prompts guided Multimodal Entity Linking (VP-MEL) task. Given a text-image pair, VP-MEL aims to link a marked region (i.e., visual prompt) in an image to its corresponding entities in the knowledge base. To facilitate this task, we present a new dataset, VPWiki, specifically designed for VP-MEL. Furthermore, we propose a framework named IIER, which enhances visual feature extraction using visual prompts and leverages the pre-trained Detective-VLM model to capture latent information. Experimental results on the VPWiki dataset demonstrate that IIER outperforms baseline methods across multiple benchmarks for the VP-MEL task.

VP-MEL: Visual Prompts Guided Multimodal Entity Linking

Large Language Models (LLMs) have become ubiquitous in today's technological landscape, boasting a plethora of applications, and even endangering human jobs in complex and creative fields. One such field is journalism: LLMs are being used for summarization, generation and even fact-checking. However, in today's political landscape, LLMs could accentuate tensions if they exhibit political bias. In this work, we evaluate the political bias of the most used 15 multilingual LLMs via the Political Compass Test. We test different scenarios, where we vary the language of the prompt, while also assigning a nationality to the model. We evaluate models on the 50 most populous countries and their official languages. Our results indicate that language has a strong influence on the political ideology displayed by a model. In addition, smaller models tend to display a more stable political ideology, i.e. ideology that is less affected by variations in the prompt.

Navigating the Political Compass: Evaluating Multilingual LLMs across Languages and Nationalities

Radiology report generation (RRG) requires advanced medical image analysis, effective temporal reasoning, and accurate text generation. While multimodal large language models (MLLMs) align with pre-trained vision encoders to enhance visual-language understanding, most existing methods rely on single-image analysis or rule-based heuristics to process multiple images, failing to fully leverage temporal information in multi-modal medical datasets. In this paper, we introduce **Libra**, a temporal-aware MLLM tailored for chest X-ray report generation. Libra combines a radiology-specific image encoder with a novel Temporal Alignment Connector (**TAC**), designed to accurately capture and integrate temporal differences between paired current and prior images. Extensive experiments on the MIMIC-CXR dataset demonstrate that Libra establishes a new state-of-the-art benchmark among similarly scaled MLLMs, setting new standards in both clinical relevance and lexical accuracy. All source code and data are publicly available at: https://github.com/X-iZhang/Libra.

Libra: Leveraging Temporal Images for Biomedical Radiology Analysis

How can a monolingual English speaker determine whether an automatic translation in French is good enough to be shared? Existing MT error detection and quality estimation (QE) techniques do not address this practical scenario. We introduce AskQE, a question generation and answering framework designed to detect critical MT errors and provide actionable feedback, helping users decide whether to accept or reject MT outputs even without the knowledge of the target language. We propose an optimized version of AskQE using LLaMA-3 70B given entailed facts during question generation. We evaluate our method on the ContraTICO dataset across five language pairs, and show that AskQE effectively identifies critical MT errors with high correlations with established QE metrics. We further extend our analysis on the BioMQM dataset of naturally occurring MT errors, where we show that AskQE has higher Kendall's Tau correlation and decision accuracy with human ratings compared to other QE metrics.

AskQE: Question Answering as Automatic Evaluation for Machine Translation

Recent advancements in multimodal Large Language Models (LLMs) have significantly enhanced the automation of medical image analysis, particularly in generating radiology reports from chest X-rays (CXR). However, these models still suffer from hallucinations and clinically significant errors, limiting their reliability in real-world applications. In this study, we propose Look & Mark (L&M), a novel grounding fixation strategy that integrates radiologist eye fixations (Look) and bounding box annotations (Mark) into the LLM prompting framework. Unlike conventional fine-tuning, L&M leverages in-context learning to achieve substantial performance gains without retraining. When evaluated across multiple domain-specific and general-purpose models, L&M demonstrates significant gains, including a 1.2% improvement in overall metrics (A.AVG) for CXR-LLaVA compared to baseline prompting and a remarkable 9.2% boost for LLaVA-Med. General-purpose models also benefit from L&M combined with in-context learning, with LLaVA-OV achieving an 87.3% clinical average performance (C.AVG)—the highest among all models, even surpassing those explicitly trained for CXR report generation. Expert evaluations further confirm that L&M reduces clinically significant errors (by 0.43 average errors per report), such as false predictions and omissions, enhancing both accuracy and reliability. These findings highlight L&M's potential as a scalable and efficient solution for AI-assisted radiology, paving the way for improved diagnostic workflows in low-resource clinical settings.

Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generation

Sequential recommenders predict users’ next interactions based on historical behavior and are essential in modern recommendation systems. While Large Language Models (LLMs) show promise, their size and high inference costs limit deployment on resource-constrained devices. Small Language Models (SLMs) provide a more efficient alternative for edge devices, but bridging the recommendation performance gap between LLMs and SLMs remains challenging. Typical approaches like supervised fine-tuning or vanilla knowledge distillation (KD) often lead to suboptimal performance or even negative transfer. Our motivational experiments reveal key issues with vanilla KD methods: feature imitation suffers from redundancy and uneven recommendation ability across layers, while prediction mimicking faces conflicts caused by differing weight distributions of prediction heads. To address these challenges, we propose a simple yet effective framework, C2KD, to transfer task-relevant knowledge from two complementary dimensions. Specifically, our method incorporates: (1) cross-layer feature imitation, which uses a dynamic router to select the most relevant teacher layers and assimilate task-relevant knowledge from the teacher’s late layers, allowing the student to concentrate on the teacher’s specialized knowledge; and (2) cross-head logit distillation, which maps the intermediate features of the student to the teacher’s output head, thereby minimizing prediction discrepancies between the teacher and the student. Extensive experiments across diverse model families demonstrate that our approach enables 1B-parameter SLMs to achieve competitive performance compared to LLMs (e.g., Llama3-8B), offering a practical solution for real-world on-device sequential recommendations.

C2KD: Cross-layer and Cross-head Knowledge Distillation for Small Language Model-based Recommendation

Recently, action-based decision-making in open-world environments has gained significant attention. Visual Language Action (VLA) models, pretrained on large-scale web datasets, have shown promise in decision-making tasks. However, previous work has primarily focused on action post-training, often neglecting enhancements to the foundation model itself. In response, we introduce a novel approach, **Act from Visual Language Post-Training**, which refines Visual Language Models (VLMs) through visual and linguistic guidance in a self-supervised manner. This enhancement improves the models’ capabilities in world knowledge, visual recognition, and spatial grounding in open-world environments. Our experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Additionally, we show that our approach outperforms traditional imitation learning-based VLA models in Minecraft. We will open-source the code, models, and datasets to foster further research.

Learning to Better Act by Post-training on Vision Language Tasks

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the mechanisms driving knowledge transfer remain underexplored. In this work, we present the first large-scale empirical and statistical analysis of KD across models ranging from 0.5B to 7B parameters on 14 complex reasoning tasks in a zero-shot setting. Our findings reveal that KD can improve the average performance of smaller models by up to 10%, with a peak task specific gain of 22%, while providing only marginal benefits (∼ 1.3%) for larger models. Surprisingly, teacher performance has a minimal impact on student outcomes, while teacher task expertise impacts KD effectiveness. A correlation study indicates that smaller LMs benefit more from KD, whereas larger LMs show diminished gains. Additionally, we uncover a misalignment between improvements in student performance and reasoning fidelity, suggesting that while KD enhances accuracy, it does not always maintain the structured decision-making processes of the teacher. Our ablation study further highlights the importance of teacher signals and logit smoothing in influencing students’ performance after distillation. Overall, our study offers a comprehensive empirical and statistical assessment of KD, highlighting both its benefits and trade-offs when distilling knowledge from larger to smaller LMs.

Downloads

Next from ACL 2025

RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery

Similar lecture

LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning