United States

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence calibration methods, largely developed for text-only LLMs, typically optimize a single holistic confidence score using binary answer-level correctness. This design is mismatched to LVLMs: an incorrect prediction may arise from perceptual failures or from reasoning errors given correct perception, and a single confidence conflates these sources while visual uncertainty is often dominated by language priors. To address these issues, we propose VL-Calibration, a reinforcement learning framework that explicitly decouples confidence into visual and reasoning confidence. To supervise visual confidence without ground-truth perception labels, we introduce an intrinsic visual certainty estimation that combines (i) visual grounding measured by KL-divergence under image perturbations and (ii) internal certainty measured by token entropy. We further propose token-level advantage reweighting to focus optimization on tokens based on visual certainty, suppressing ungrounded hallucinations while preserving valid perception. Experiments on thirteen benchmarks show that VL-Calibration effectively improves calibration while boosting visual reasoning accuracy, and it generalizes to out-of-distribution benchmarks across model scales and architectures.

ACL 2026

VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning

### 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)

technical paper

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

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

Large language models (LLMs) are increasingly adopted as scalable judges for open-ended generation, yet how they form judgments remains insufficiently understood. Meanwhile, modern LLMs frequently produce answers accompanied by explicit reasoning, making reasoning chains a natural but understudied source of information for model-based evaluation. This work takes a first step toward understanding how exposing reasoning influences LLM-based judgment. Empirical results across factual question-answering (QA) and mathematical datasets show that the presence of reasoning substantially alters judgment behavior, with clear differences across judge capabilities. Weaker judges become more likely to accept incorrect answers when reasoning is present, suggesting over-reliance on persuasive explanations. In contrast, stronger judges exhibit more selective behavior and, in some cases, achieve higher judgment accuracy by leveraging reasoning content. Further analysis reveals that both reasoning fluency and factuality critically shape judgment outcomes. Together, these findings suggest that examining how models interpret reasoning is essential for understanding and improving LLM-based evaluation, with broader implications for the design of reliable automatic judges and evaluation protocols.

How Long Reasoning Chains Influence LLMs’ Judgment of Answer Factuality

Fine-grained emotion classification (FEC) requires distinguishing subtly different emotions, where the dominant errors come from closely confusable categories. Recent progress relies on contrastive learning with hard-pair mining, implicitly assuming that a fixed similarity metric is sufficient to optimize informative pairs. We argue that this assumption is fragile because defining whether two utterances are similar becomes a problem when the label space is crowded, and hard-pair mining under a fixed metric can systematically miss the worst confusions. Thus, we treat the similarity function as a learnable component and design an adversarial metric learning (AML) framework. It follows theoretical interpretations of metric-robust representations that better separate confusable emotions. AML trains a pairwise discriminator to maximally confuse two targeted hard pair types, while training the encoder to remain discriminative under this worst-case learned metric. Our code and data are released on GitHub.

Adversarial Metric Learning for Fine-Grained Emotion Classification

Large language models (LLMs) have advanced natural language processing, but their massive parameter counts create computational and memory challenges during deployment. Post-training quantization (PTQ) has emerged as a promising approach to mitigate these challenges. While existing PTQ methods can effectively quantize LLMs, they experience substantial accuracy loss at extremely low bit-widths due to high-impact parameters. Several approaches address this by retaining high-impact parameters in FP16 format, but they apply fixed ratios across all layers, overlooking layer-wise sensitivity variations. We propose a quadratic optimization framework that determines layer-specific ratios of high-impact parameters while considering inter-layer dependencies. We quantize high-impact parameters to moderate bit-widths while the remaining parameters are quantized to extremely low bit-widths. Under the same resource budget, this preserves more high-impact parameters than methods retaining a few in FP16 format. Our framework enables leveraging advanced quantization methods for high-impact parameters while applying lightweight computational quantization methods to the rest, achieving an effective balance between computational efficiency and accuracy during quantization process.

Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models

Recent studies posit that Reinforcement Learning with Verifiable Rewards (RLVR) primarily amplifies behaviors inherent to the pre-training distribution rather than inducing new capabilities, but these insights are predominantly limited to language-only domains, leaving the dynamics of visual-centric spatial reasoning under-explored. To examine the impact of RLVR on the capability boundaries of Vision-Language Models (VLMs), we introduce Ariadne, a controlled framework based on synthetic maze navigation where the reasoning difficulty is precisely regulated by path length and the number of turns. We demonstrate that applying RLVR extends the spatial reasoning boundary, achieving success on problems where the base policy VLM consistently attains $0\%$ accuracy despite increasing pass@k sampling budgets, indicating that the optimized policy successfully navigates search spaces that were effectively unreachable by the base distribution. Furthermore, despite being trained exclusively on synthetic mazes, we evaluate the model on two real-world navigation benchmarks (MapBench and ReasonMap) in a zero-shot setting. The observed improvements in these out-of-domain tasks suggest genuine spatial reasoning capability expansion rather than mere sampling efficiency. Our code is available at: https://github.com/MingheShen/Ariadne

Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models

Despite the recent progress made in cross-prompt essay scoring, there is little analysis of what makes a state-of-the-art cross-prompt scorer work well. To this end, we present an empirical analysis of how the key components of a cross-prompt scorer interact with each other and impact its overall performance. In addition, we examine for the first time the application of transductive learning to cross-prompt scoring, which represents an important starting point for providing a practical way to improve cross-prompt scorers for use in the rarely-studied classroom setting without the need for additional labeled training data.

Cross-Prompt Automated Essay Scoring of Multiple Traits: Making Sense of the State of the Art

Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model. However, existing methods struggle to maintain performance gains as the number of merged models increases. In this paper, we investigate the key obstacles that limit the scalability of model merging. We prove that the limited effective parameter space imposes a strict constraint on the number of models that can be successfully merged. Through Gaussian Width analysis, we show that marginal benefits diminish according to a strictly concave function as more models are merged. Using Approximate Kinematics Theory, we further prove the existence of a unique optimal threshold beyond which additional models yield negligible improvements. To address this limitation, we propose a straightforward Reparameterized Heavy-Tailed method to extend the merged model's coverage and enhance performance. Empirical results on 19 benchmarks, including both knowledge-intensive and general-purpose tasks, validate our theoretical analysis. We believe that these results spark further research beyond the current scope of model merging.

Why Do More Experts Fail? A Theoretical Analysis of Model Merging

Emotion plays a pivotal role in shaping negotiation outcomes, influencing trust, cooperation, and long-term relationships. Developing negotiation dialog systems that can recognize and respond strategically to emotions is therefore essential to create more effective human-centered interactions. Beyond generating emotionally appropriate responses, interpretability - understanding how a system generates a particular emotion-aware response, is critical for fostering reliability and building rapport. Driven by these aspects, in this work, we introduce PRISMA, an interpretable emotionally intelligent negotiation dialogue system targeting two application domains, viz. job interviews and resource allocation. To enable interpretability, we propose an Emotion-aware Negotiation Strategy-informed Chain-of-Thought (ENS-CoT) reasoning mechanism, which mimics human negotiation by perceiving, understanding, using, and managing emotions. Leveraging ENS-CoT, we curate two new datasets: JobNego (for job interview negotiation) and ResNego (for resource allocation negotiation). We then leverage these datasets to develop PRISMA by augmenting self-training with Direct Preference Optimization (DPO), guiding agents toward more accurate, interpretable, and emotionally appropriate negotiation responses. Automatic and human evaluations on JobNego and ResNego datasets demonstrate that PRISMA substantially enhances the interpretability and generates appropriate emotion-aware responses, while improving overall negotiation effectiveness.

PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues

Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (CoT), which significantly increase computational overhead. 
To address this overthinking problem, existing work focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. 
Unfortunately, using RL will suffer the the reward hacking problem, e.g., the model engages in thinking but is judged as not doing so, resulting in incorrect rewards.
To mitigate this problem, existing works either employ supervised fine-tuning (SFT), which incurs high computational costs, or enforce uniform token limits on non-thinking responses, which yields limited mitigation of the problem.
In this paper, we propose Thinking-Based Non-Thinking (TNT). It does not employ SFT, and sets different maximum token usage for responses not using thinking across various queries by leveraging information from the solution component of the responses using thinking. Experiments on five mathematical benchmarks demonstrate that TNT reduces token usage by around $50\\%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5B, while significantly improving accuracy. In fact, TNT achieves the optimal trade-off between accuracy and efficiency among all tested methods. Additionally, the probability of reward hacking problem in TNT’s responses, which are classified as not using thinking, remains below $10\\%$ across all tested datasets.

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive. We propose \textbf{Doc-$V^*$}, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation. \textbf{Doc-$V^*$} begins with a thumbnail overview, then actively navigates via semantic retrieval and targeted page fetching, and aggregates evidence in a structured working memory for grounded reasoning. Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, \textbf{Doc-$V^*$} balances answer accuracy with evidence-seeking efficiency. Across five benchmarks, \textbf{Doc-$V^*$} outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to \textbf{47.9\%} over RAG baseline. Other results reveal effective evidence aggregation with selective attention, not increased input pages.

Doc-$V^*$: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and hinder downstream applications like chatbots and voice assistants. If left unaddressed, such disfluencies can significantly degrade the reliability of downstream systems. Most existing approaches rely on classical models that focus on identifying disfluent tokens for removal. While this strategy is effective to some extent, it often disrupts grammatical structure and semantic coherence, leading to incomplete or unnatural sentences. Recent literature explored the use of large language models (LLMs); however, these efforts have primarily focused on disfluency detection or data augmentation, rather than performing comprehensive correction. We propose a multilingual correction pipeline where a sequence tagger first marks disfluent tokens, and these signals guide instruction fine-tuning of an LLM to rewrite transcripts into fluent text. To further improve reliability, we add a contrastive learning objective that penalizes the reproduction of disfluent tokens, encouraging the model to preserve grammar and meaning while removing disfluent artifacts. Our experiments across three Indian languages, namely Hindi, Bengali, and Marathi show consistent improvements over strong baselines, including multilingual sequence-to-sequence models. These results highlight that detection-only strategies are insufficient. Combining token-level cues with instruction tuning and contrastive learning provides a practical and scalable solution for multilingual disfluency correction in speech-driven NLP systems. We make the codes publicly available at https://github.com/deepak-kumar-98/Mind-the-Pause.

Downloads

Next from ACL 2026

How Long Reasoning Chains Influence LLMs’ Judgment of Answer Factuality

Similar lecture

Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models