Austria

Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in aligning LLMs with human preferences, it is less suitable for multi-step reasoning tasks because (1) DPO relies on paired preference data, which is not readily available for multi-step reasoning tasks, and (2) it treats all tokens uniformly, making it ineffective for credit assignment in multi-step reasoning tasks, which often come with sparse reward. In this work, we propose OREO (Offline REasoning Optimization), an offline RL method for enhancing LLM multi-step reasoning. Building on insights from previous works of maximum entropy reinforcement learning, it jointly learns a policy model and value function by optimizing the soft Bellman Equation. We show in principle that it reduces the need to collect pairwise data and enables better credit assignment. Empirically, OREO surpasses existing offline learning methods on multi-step reasoning benchmarks, including mathematical reasoning tasks (GSM8K, MATH), and embodied agent control (ALFWorld). The approach can be extended to a multi-iteration framework when additional resources are available. Furthermore, the learned value function can be leveraged to guide the tree search for free, which can further boost the performance during test time.

ACL 2025

Offline Reinforcement Learning for LLM Multi-step Reasoning

multi-step reasoning

reasoning

reinforcement learning

### 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)

poster

Recent advancements in multi-turn voice interaction models have improved user-model communication. However, while closed-source models effectively retain and recall past utterances, whether open-source models share this ability remains unexplored. To fill this gap, we systematically evaluate how well open-source interaction models utilize past utterances using ContextDialog, a benchmark we proposed for this purpose. Our findings show that speech-based models have more difficulty than text-based ones, especially when recalling information conveyed in speech, and even with retrieval-augmented generation, models still struggle with questions about past utterances. These insights highlight key limitations in open-source models and suggest ways to improve memory retention and retrieval robustness.

Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models

Multimodal Large Language Models (MLLMs) are measured on numerous benchmarks like image captioning, visual question answer, and reasoning. However, these benchmarks often include overly simple or uninformative samples, making it difficult to effectively distinguish the performance of different MLLMs. Additionally, evaluating models across many benchmarks creates a significant computational burden. To address these issues, we propose LIME (Less Is More for MLLM Evaluation), a refined and efficient benchmark curated using a semi-automated pipeline. This pipeline filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding. Our experiments show that LIME reduces the number of samples by 76% and evaluation time by 77%, while it can more effectively distinguish different models' abilities. Notably, we find that traditional automatic metrics like CIDEr are insufficient for evaluating MLLMs’ captioning performance, and excluding the caption task score yields a more accurate reflection of overall model performance. All code and data are available at https://anonymous.4open.science/r/LIME-49CD

LIME: Less Is More for MLLM Evaluation

Narrative frames are a powerful way of conceptualizing and communicating complex, controversial ideas. However, while the impact of narrative framing in media has been widely acknowledged, few NLP studies have considered the aspects which make them an effective framing device. In this paper, we show how elements of narrativity in such frames link to fundamental aspects of framing, and present a framework which formalizes and operationalizes such aspects. We annotate and release a data set of news articles in the climate change domain, and perform extensive experiments with LLMs to test their ability to understand narrative frames and their components. Then, we apply the framework in an unsupervised way to discover components of narrative framing in an unrelated domain of COVID-19 crisis, and show how it can generalize across topics to arrive at insights consistent with theoretical narrative framing analysis.

A Framework of Narrative Media Framing in Political Discourse

We introduce semantic topology, a novel framework for discourse analysis that leverages Circuit Topology to quantify the semantic arrangement of sentences in a text. By mapping recurring themes as series, parallel, or cross relationships, we identify statistical differences in communication patterns in long-form true and fake news. Our analysis of large-scale news datasets reveals that true news are more likely to exhibit more complex topological structures, with greater thematic interleaving and long-range coherence, whereas fake news favor simpler, more linear narratives. These findings suggest that topological features capture stylistic distinctions beyond traditional linguistic cues, offering new insights for discourse modeling.

Semantic Topology: a New Perspective for Communication Style Characterization

We release a parallel corpus for medical text simplification, which paraphrases medical terms into expressions easily understood by patients. Medical texts written by medical practitioners contain a lot of technical terms, and patients who are non-experts are often unable to use the information effectively. Therefore, there is a strong social demand for medical text simplification that paraphrases input sentences without using medical terms. However, this task has not been sufficiently studied in non-English languages. We therefore developed parallel corpora for medical text simplification in nine languages: German, English, Spanish, French, Italian, Japanese, Portuguese, Russian, and Chinese, each with 10,000 sentence pairs, by automatic sentence alignment to online medical references for professionals and consumers. We also propose a method for training text simplification models to actively paraphrase complex expressions, including medical terms. Experimental results show that the proposed method improves the performance of medical text simplification. In addition, we confirmed that training with a multilingual dataset is more effective than training with a monolingual dataset.

MultiMSD: A Corpus for Multilingual Medical Text Simplification from Online Medical References

Multi-turn instruction following capability constitutes a core competency of large language models (LLMs) in real-world applications. Existing evaluation benchmarks predominantly focus on fine-grained constraint satisfaction and domain-specific capability assessment, yet overlook the crucial structural dependency between dialogue turns that distinguishes multi-turn from single-turn interactions. This structural dependency not only reflects user intent but also establishes a second dimension for instruction following evaluation beyond constraint satisfaction. To address this gap, we propose StructFlowBench, a multi-turn instruction following benchmark with structural flow modeling. The benchmark innovatively defines a structural flow framework comprising six fundamental inter-turn relationships, which not only introduces novel structural constraints for model evaluation but also serves as generation parameters for creating customized dialogue flows tailored to specific scenarios. Adopting established LLM-based automatic evaluation methodologies, we conduct systematic evaluations of 13 leading open-source and closed-source LLMs. Experimental results reveal significant deficiencies in current models' comprehension of multi-turn dialogue structures.

StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following

Financial markets exhibit complex dynamics where localized events trigger ripple effects across entities. Previous event studies, constrained by static single-companies analyses and simplistic assumptions, fail to capture these ripple effects. While large language models (LLMs) offer emergent reasoning capabilities, their direct application falters due to structural market unawareness and limited capacity to analyze ripple effects. We propose FinRipple, an elegant framework that empowers LLMs with the ability to analyze ripple effects through financial theory-guided large-scale reinforcement learning. We begin by relaxing the assumptions of previous methods, incorporating a time-varying knowledge graph to accurately represent market structure. By seamlessly integrating classical asset pricing theory, we align the LLM with the market, enabling it to predict ripple effects. To the best of our knowledge, we are the first to provide a standardized definition of ripple effect prediction, a task that is extremely important yet unexplored in the financial domain. Extensive experiments demonstrate that FinRipple provides a promising solution to this task.

FinRipple: Aligning Large Language Models with Financial Market for Event Ripple Effect Awareness

Eligibility criteria (EC) are critical components of clinical trial design, defining the parameters for participant inclusion and exclusion. However, designing EC remains a complex, expertise-intensive process. Traditional approaches to EC generation often rely on user-prompted predefined categories, which limit adaptability and may fail to produce comprehensive, contextually appropriate criteria. To address these challenges, we introduce EC-RAFT, a method that utilizes Retrieval-Augmented Fine-Tuning (RAFT) to generate structured and cohesive EC directly from clinical trial titles and descriptions. EC-RAFT integrates contextual retrieval, synthesized intermediate reasoning, and fine-tuned language models to produce comprehensive EC sets. To enhance clinical alignment evaluation with referenced criteria, we also propose an LLM-guided evaluation pipeline. Our results demonstrate that our solution, which uses Llama-3.1-8B-Instruct as a base model, achieves a BERTScore of 86.23 and an EC-matched LLM-as-a-Judge score of 1.66 out of 3, outperforming zero-shot Llama-3.1 and Gemini-1.5 by 0.41 and 0.11 points, respectively. EC-RAFT was trained in a low-cost setup and, therefore, can be used as a practical solution for EC generation while ensuring quality and relevance in clinical trial design.

EC-RAFT: Automated Generation of Clinical Trial Eligibility Criteria through Retrieval-Augmented Fine-Tuning

Inverse tasks can uncover potential reasoning gaps as Large Language Models (LLMs) scale up. In this work, we explore the redefinition task, in which we assign alternative values to well-known physical constants and units of measure, prompting LLMs to respond accordingly. Our findings show that not only does model performance degrade with scale, but its false confidence also rises. Moreover, while factors such as prompting strategies or response formatting are influential, they do not preclude LLMs from anchoring to memorized values.

Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models

Large Language Models (LLMs) are being used more and more extensively for automated evaluation in various scenarios. Previous studies have attempted to fine-tune open-source LLMs to replicate the evaluation explanations and judgments of powerful proprietary models, such as GPT-4. However, these methods are largely limited to text-based analyses under predefined general criteria, resulting in reduced adaptability for unseen instructions and demonstrating instability in evaluating adherence to quantitative and structural constraints. To address these limitations, we propose a novel evaluation framework, ARJudge, that adaptively formulates evaluation criteria and synthesizes both text-based and code-driven analyses to evaluate LLM responses. ARJudge consists of two components: a fine-tuned Analyzer that generates multi-faceted evaluation analyses and a tuning-free Refiner that combines and refines all analyses to make the final judgment. We construct a Composite Analysis Corpus that integrates tasks for evaluation criteria generation alongside text-based and code-driven analysis generation to train the Analyzer. Our results demonstrate that ARJudge outperforms existing fine-tuned evaluators in effectiveness and robustness. Furthermore, it demonstrates the importance of multi-faceted evaluation and code-driven analyses in enhancing evaluation capabilities.

Downloads

Next from ACL 2025

Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models

Similar lecture

LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs