Austria

Requiring a large language model (LLM) to generate intermediary reasoning steps, known as Chain of Thought (CoT), has been shown to be an effective way of boosting performance. Previous approaches have focused on generating multiple independent CoTs, combining them through ensembling or other post-hoc strategies to enhance reasoning. In this work, we introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step, which is fundamentally different from prior work that primarily operate on parallel CoT generations. DCoT allows LLMs to gain the ability to perform within-inference refinement of reasoning chains without requiring external feedback. Through a rigorous set of experiments spanning a wide range of tasks that require various reasoning types, we show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales (1.3B to 70B). These improvements are particularly impactful for tasks with a large result state space, such as those involving numeric answers. Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models&#39; ability to refine an initial reasoning chain by generating a second, improved chain within the same inference step, demonstrating previously elusive self-improvement. Our code and data are publicly available.

ACL 2025

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs

self-improvement

reasoning

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

Requiring a large language model (LLM) to generate intermediary reasoning steps, known as Chain of Thought (CoT), has been shown to be an effective way of boosting performance. Previous approaches have focused on generating multiple independent CoTs, combining them through ensembling or other post-hoc strategies to enhance reasoning. In this work, we introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step, which is fundamentally different from prior work that primarily operate on parallel CoT generations. DCoT allows LLMs to gain the ability to perform within-inference refinement of reasoning chains without requiring external feedback. Through a rigorous set of experiments spanning a wide range of tasks that require various reasoning types, we show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales (1.3B to 70B). These improvements are particularly impactful for tasks with a large result state space, such as those involving numeric answers. Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain by generating a second, improved chain within the same inference step, demonstrating previously elusive self-improvement. Our code and data are publicly available.

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)

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and decision-making tasks as conversation partners to improve productivity. Thus, conformity to incorrect responses can compromise their effectiveness. In this paper, we adapt psychological experiments to examine the extent of conformity in state-of-the-art LLMs. Our findings reveal that all models tested exhibit varying levels of conformity toward the majority, regardless of their initial choice or correctness, across different knowledge domains. Notably, we are the first to show that LLMs are more likely to conform when they are more uncertain in their own prediction. We further explore factors that influence conformity, such as training paradigms and input characteristics, finding that instruction-tuned models are less susceptible to conformity, while increasing the naturalness of majority tones amplifies conformity. Finally, we propose two interventions—Devil's Advocate and Question Distillation—to mitigate conformity, providing insights into building more robust language models.

Conformity in Large Language Models

Interpreting the law is always essential for the law to adapt to the ever-changing society. It is a critical and challenging task even for legal practitioners, as it requires meticulous and professional annotations and summarizations by legal experts, which are admittedly time-consuming and expensive to collect at scale. To alleviate the burden on legal experts, we propose a method for automated legal interpretation. Specifically, by emulating doctrinal legal research, we introduce a novel framework, **ATRIE**, to address Legal Concept Interpretation, a typical task in legal interpretation. **ATRIE** utilizes large language models (LLMs) to **A**u**T**omatically **R**etrieve concept-related information, **I**nterpret legal concepts, and **E**valuate generated interpretations, eliminating dependence on legal experts. ATRIE comprises a legal concept interpreter and a legal concept interpretation evaluator. The interpreter uses LLMs to retrieve relevant information from previous cases and interpret legal concepts. The evaluator uses performance changes on Legal Concept Entailment, a downstream task we propose, as a proxy of interpretation quality. Automated and multifaceted human evaluations indicate that the quality of our interpretations is comparable to those written by legal experts, with superior comprehensiveness and readability. Although there remains a slight gap in accuracy, it can already assist legal practitioners in improving the efficiency of legal interpretation.

Automating Legal Concept Interpretation with LLMs: Retrieval, Generation, and Evaluation

Designing solutions for complex engineering challenges is crucial in human production activities. However, previous research in the retrieval-augmented generation (RAG) field has not sufficiently addressed tasks related to the design of complex engineering solutions. To fill this gap, we introduce a new benchmark, SolutionBench, to evaluate a system’s ability to generate complete and feasible solutions for engineering problems with multiple complex constraints. To further advance the design of complex engineering solutions, we propose a novel system, SolutionRAG, that leverages the tree-based exploration and bi-point thinking mechanism to generate reliable solutions. Extensive experimental results demonstrate that SolutionRAG achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications.

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods often face challenges such as superposition and layer-wise activation variance, which limit their reliability. Sparse Autoencoders (SAEs) offer a more nuanced analysis by decomposing the activations of LLMs into a sparse linear combination of SAE features. We introduce a novel metric to assess the monolinguality of features obtained from SAEs, discovering that some features are strongly related to specific languages. Additionally, we show that ablating these SAE features only significantly reduces abilities in one language of LLMs, leaving others almost unaffected. Interestingly, we find some languages have multiple synergistic SAE features, and ablating them together yields greater improvement than ablating individually. Moreover, we leverage these SAE-derived language-specific features to enhance steering vectors, achieving control over the language generated by LLMs. The code is publicly available at~\url{https://github.com/Aatrox103/multilingual-llm-features}.

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders

Discourse coherence theories posit relations between text spans as a key feature of coherent texts. However, existing work on coherence modeling has paid little attention to discourse relations. In this paper, we provide empirical evidence to demonstrate that relation features are correlated with text coherence. Then, we investigate a novel fusion model that uses position-aware attention and a visible matrix to combine text- and relation-based features for coherence assessment. Experimental results on two benchmarks show that our approaches can significantly improve baselines, demonstrating the importance of relation features for coherence modeling.

Discourse Relation-Enhanced Neural Coherence Modeling

The rapid advancement of large language models (LLMs) has brought about increased concerns regarding their safety, especially as adversaries develop jailbreak techniques to bypass LLMs' safety mechanism. Although recent work on safety training with modules such as low-rank adaptation (LoRA) to resist jailbreaks shows promise, these approaches can inadvertently degrade a model’s general utility. In this paper, we propose a novel plug-and-play method that mitigates the impact of safety training on model utility by explicitly locating and leveraging safety-critical singular vectors, which only contribute to safety, within the model’s parameter space. We quantify the safety-criticality of each singular vector as the difference of their importance for safety and utility measured by a corresponding low-rank projection. The top scored singular vectors are located as safety-critical and are used to initialize the LoRA modules within existing safety training methods in a plug-and-play manner, thereby constraining the training updates within safety-critical parameters. Additionally, we propose a dynamic rank number determination strategy to further reduce parameter overhead. Experiments on HarmBench with multiple jailbreak methods validate the effectiveness of our approach in safety training, while evaluations on several utility benchmarks demonstrate that our method successfully mitigates the adverse impact of safety training on model utility, enhancing the utility performance of the evaluated safety training baselines.

Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain unexplored, particularly in third-party platforms that facilitate user interactions via APIs. Existing attacks on LLM reasoning are constrained by specific settings or lack of imperceptibility, limiting their feasibility and generalizability. To address these challenges, we propose the Stepwise rEasoning Error Disruption (SEED) attack, which subtly injects errors into prior reasoning steps to mislead the model into producing incorrect subsequent reasoning and final answers. Unlike previous methods, SEED is compatible with zero-shot and few-shot settings, maintains the natural reasoning flow, and ensures covert execution without modifying the instruction. Extensive experiments on four datasets across four different models demonstrate SEED's effectiveness, revealing the vulnerabilities of LLMs to disruptions in reasoning processes. These findings underscore the need for greater attention to the robustness of LLM reasoning to ensure safety in practical applications. Our code is available at: https://github.com/Applied-Machine-Learning-Lab/SEED-Attack

Stepwise Reasoning Disruption Attack of LLMs

Multilingual language models (MLMs) store factual knowledge across languages but often struggle to provide consistent responses to semantically equivalent prompts in different languages. While previous studies point out this cross-lingual inconsistency issue, the underlying causes remain unexplored. In this work, we use mechanistic interpretability methods to investigate cross-lingual inconsistencies in MLMs. We find that MLMs encode knowledge in a language-independent concept space through most layers, and only transition to language-specific spaces in the final layers. Failures during the language transition often result in incorrect predictions in the target language, even when the answers are correct in other languages. To mitigate this inconsistency issue, we propose a linear shortcut method that bypasses computations in the final layers, enhancing both prediction accuracy and cross-lingual consistency. Our findings shed light on the internal mechanisms of MLMs and provide a lightweight, effective strategy for producing more consistent factual outputs.

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models

Readers can have different goals with respect to the text that they are reading. Can these goals be decoded from their eye movements over the text? In this work, we examine for the first time whether it is possible to distinguish between two types of common reading goals: information seeking and ordinary reading for comprehension. Using large-scale eye tracking data, we address this task with a wide range of models that cover different architectural and data representation strategies, and further introduce a new model ensemble. We find that transformer-based models with scanpath representations coupled with language modeling solve it most successfully, and that accurate predictions can be made in real time, shortly after the participant started reading the text. We further introduce a new method for model performance analysis based on mixed effect modeling. Combining this method with rich textual annotations reveals key properties of textual items and participants that contribute to the difficulty of the task, and improves our understanding of the variability in eye movement patterns across the two reading regimes.

Decoding Reading Goals from Eye Movements

Imageability (potential of text to evoke a mental image) and concreteness (perceptibility of text) are two psycholinguistic properties that link visual and semantic spaces. It is little surprise that computational methods that estimate them do so using parallel visual and semantic spaces, such as collections of image-caption pairs or multi-modal models. In this paper, we work on the supposition that text itself in an image-caption dataset offers sufficient signals to accurately estimate these properties. We hypothesize, in particular, that the peakedness of the neighborhood of a word in the semantic embedding space reflects its degree of imageability and concreteness. We then propose an unsupervised, distribution-free measure, which we call Neighborhood Stability Measure (NSM), that quantifies the sharpness of peaks. Extensive experiments show that NSM correlates more strongly with ground-truth ratings than existing unsupervised methods, and is a strong predictor of these properties for classification. Our code and data are available on GitHub (https://github.com/Artificial-Memory-Lab/imageability).

Downloads

Next from ACL 2025

Conformity in Large Language Models

Similar lecture

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens