Austria

Scaling the test-time compute of large language models has demonstrated impressive performance on reasoning benchmarks. However, existing evaluations of test-time scaling make the strong assumption that a reasoning system should always give an answer to any question provided. This overlooks concerns about whether a model is confident in its answer, and whether it is appropriate to always provide a response. To address these concerns, we extract confidence scores during reasoning for thresholding model responses. We find that increasing compute budget at inference time not only helps models answer more questions correctly, but also increases confidence in correct responses. We then extend the current paradigm of zero-risk responses during evaluation by considering settings with non-zero levels of response risk, and suggest a recipe for reporting evaluations under these settings.

ACL 2025

Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering

test-time scaling

reasoning

selective question answering

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.

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)

Multimodal learning has celebrated remarkable success across diverse areas, yet faces the challenge of prohibitively expensive data collection and annotation when adapting models to new environments. In this context, domain adaptation has gained growing popularity as a technique for knowledge transfer, which, however, remains underexplored in multimodal settings compared with unimodal ones. This paper investigates multimodal domain adaptation, focusing on a practical partially shifting scenario where some modalities (referred to as anchors) remain domain-stable, while others (referred to as drifts) undergo a domain shift. We propose a bi-alignment scheme to simultaneously perform drift-drift and anchor-drift matching. The former is achieved through adversarial learning, aligning the representations of the drifts across source and target domains; the latter corresponds to an "anchor dragging drift" strategy, which matches the distributions of the drifts and anchors within the target domain using the optimal transport (OT) method. The overall design principle features \textbf{A}dversarial \textbf{A}lignment with \textbf{A}nchor \textbf{D}ragging \textbf{D}rift, abbreviated as \textbf{$A^3D^2$}, for multimodal domain adaptation with partially shifted modalities. Comprehensive empirical results verify the effectiveness of the proposed approach, and demonstrate that $A^3D^2$ achieves superior performance compared with state-of-the-art approaches. The code is available at: \url{https://github.com/sunjunaimer/A3D2.git}.

Adversarial Alignment with Anchor Dragging Drift (A3D2): Multimodal Domain Adaptation with Partially Shifted Modalities

Retrieval-augmented generation (RAG) helps address the limitations of parametric knowledge embedded within a language model (LM). In real world settings, retrieved information can vary in complexity, yet most investigations of LM utilisation of context has been limited to synthetic text. We introduce DRUID (Dataset of Retrieved Unreliable, Insufficient and Difficult-to-understand contexts) with real-world queries and contexts manually annotated for stance. The dataset is based on the prototypical task of automated claim verification, for which automated retrieval of real-world evidence is crucial. We compare DRUID to synthetic datasets (CounterFact, ConflictQA) and find that artificial datasets often fail to represent the complexity and diversity of realistically retrieved context. We show that synthetic datasets exaggerate context characteristics rare in real retrieved data, which leads to inflated context utilisation results, as measured by our novel ACU score. Moreover, while previous work has mainly focused on singleton context characteristics to explain context utilisation, correlations between singleton context properties and ACU on DRUID are surprisingly small compared to other properties related to context source. Overall, our work underscores the need for real-world aligned context utilisation studies to represent and improve performance in real-world RAG settings.

A Reality Check on Context Utilisation for Retrieval-Augmented Generation

Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered significant attention due to their potential to automate complex development tasks, assist in debugging, and enhance productivity. However, existing approaches often struggle with sub-optimal decision-making, requiring either extensive manual intervention or inefficient compute scaling strategies. To improve coding agent performance, we present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents, that is faster and more effective at recovering from sub-optimal decisions compared to baselines. While traditional agents either follow linear trajectories or rely on random sampling for scaling compute, our approach DARS works by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt from that point. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2. Our framework achieves a pass@1 rate of 47%, outperforming state-of-the-art (SOTA) open-source frameworks.

DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal

Multi-task learning (MTL) enhances efficiency by sharing representations across tasks, but task dissimilarities often cause partial learning, where some tasks dominate while others are neglected. Existing methods mainly focus on balancing loss or gradients but fail to fundamentally address this issue due to the representation discrepancy in latent space. In this paper, we propose variance-invariant probabilistic decoding for multi-task learning (VIP-MTL), a framework that ensures impartial learning by harmonizing representation spaces across tasks. VIP-MTL decodes shared representations into task-specific probabilistic distributions and applies variance normalization to constrain these distributions to a consistent scale. Experiments on two language benchmarks show that VIP-MTL outperforms 12 representative methods under the same multi-task settings, especially in heterogeneous task combinations and data-constrained scenarios. Further analysis shows that VIP-MTL is robust to sampling distributions, efficient on optimization process, and scale-invariant to task losses. Additionally, the learned task-specific representations are more informative, enhancing the language understanding abilities of pre-trained language models under the multi-task paradigm.

Impartial Multi-task Representation Learning via Variance-invariant Probabilistic Decoding

Large language models (LLMs) have recently pushed open-domain question answering (ODQA) to new frontiers. However, prevailing retriever–reader pipelines often depend on multiple rounds of prompt-level instructions, leading to high computational overhead, instability, and suboptimal retrieval coverage. In this paper, we propose EmbQA, an embedding-level framework that alleviates these shortcomings by enhancing both the retriever and the reader. Specifically, we refine query representations via lightweight linear layers under an unsupervised contrastive learning objective, thereby reordering retrieved passages to highlight those most likely to contain correct answers. Additionally, we introduce an exploratory embedding that broadens the model’s latent semantic space to diversify candidate generation and employs an entropy-based selection mechanism to choose the most confident answer automatically. Extensive experiments across three open-source LLMs, three retrieval methods, and four ODQA benchmarks demonstrate that EmbQA substantially outperforms recent baselines in both accuracy and efficiency.

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering

Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks mainly focus more on the end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization. Instead, we introduce WE-MATH, the first benchmark specifically designed to explore the problem-solving principles. We meticulously collect 6.5K visual math problems and decompose them into 10.9K step-level questions for evaluation, spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts. Specifically, we decompose composite problems into sub-problems according to the required knowledge concepts and introduce a novel four-dimensional metric to hierarchically assess inherent issues in LMMs’ reasoning process. With WE-MATH, we conduct a thorough evaluation of existing LMMs in visual mathematical reasoning and provide comprehensive analysis and insight for future development. We anticipate that WE-MATH will open new pathways for advancements in visual mathematical reasoning for LMMs. Data and code are available at https://github.com/We-Math/We-Math.

WE-MATH: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?

When aligning large language models (LLMs), their performance across various tasks (such as being helpful, harmless, and honest) is heavily influenced by the composition of the training data. However, it is difficult to determine what mixture of data should be used to produce a model with strong performance across all tasks. Existing approaches rely on large ablation studies, heuristics, or human intuition, though these can be prohibitively expensive and suboptimal. We study this problem in the context of preference optimization via DPO and propose a novel and theoretically justified algorithm, AutoMixAlign (AMA), that adaptively mixes datasets during LLM training to balance performance across multiple tasks. AMA first trains \textit{specialist models} for each task to determine losses that corresponding to strong task performance. Next, AMA trains a generalist model using a novel minimax optimization that prioritizes tasks for which generalist model losses are furthest from specialist model losses. We introduce two algorithms to optimize this problem: (1) AMA-R adaptively reweights the objective to prioritize tasks, and (2) AMA-S adaptively adjusts how much data is sampled from each task to prioritize tasks. Both algorithms achieve a convergence rate of $O(1/\sqrt{T})$ in the convex case. AMA-R's convergence result immediately follows from Sagawa et. al, 2019, and we provide a convergence proof for AMA-S using techniques from online learning such as EXP3 (Auer et. al, 2002). We evaluate AMA on several multitask alignment setups, and observe that AMA outperforms the standard alignment approach which simply optimizes the total loss across all tasks and also outperforms model-merging methods.

AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs

As the scale of training large language models (LLMs) increases, one emergent failure is silent data corruption (SDC), where hardware produces incorrect computations without explicit failure signals. In this work, we are the first to investigate the impact of real-world SDCs on LLM training by comparing model training between healthy production nodes and unhealthy nodes exhibiting SDCs. With the help from a cloud computing platform, we access the unhealthy nodes that were swept out from production by automated fleet management. Using deterministic execution via XLA compiler and our proposed synchronization mechanisms, we isolate and analyze the impact of SDC errors on these nodes at three levels: at each submodule computation, at a single optimizer step, and at a training period. Our results reveal that the impact of SDCs on computation varies on different unhealthy nodes. Although in most cases the perturbations from SDCs on submodule computation and gradients are relatively small, SDCs can lead models to converge to different optima with different weights and even cause spikes in the training loss. Our analysis sheds light on further understanding and mitigating the impact of SDCs.

Understanding Silent Data Corruption in LLM Training

Language learners encounter a wide range of grammar items across the beginner, intermediate, and advanced levels.
To develop grammatical error correction (GEC) models effectively, it is crucial to identify which grammar items are easier or more challenging for models to correct. However, conventional benchmarks based on learner-produced texts are insufficient for conducting detailed evaluations of GEC model performance across a wide range of grammar items due to biases in their distribution.
To address this issue, we propose a new evaluation paradigm that assesses GEC models using minimal pairs of ungrammatical and grammatical sentences for each grammar item. As the first benchmark within this paradigm, we introduce the CEFR-based Targeted Syntactic Evaluation Dataset for Grammatical Error Correction (CTSEG), which complements existing English benchmarks by enabling fine-grained analyses previously unattainable with conventional datasets. Using CTSEG, we evaluate three mainstream types of English GEC models: sequence-to-sequence models, sequence tagging models, and prompt-based models. The results indicate that while current models perform well on beginner-level grammar items, their performance deteriorates substantially for intermediate and advanced items.

Targeted Syntactic Evaluation for Grammatical Error Correction

Multimodal Large Language Models (MLLMs) are renowned for their superior instruction-following and reasoning capabilities across diverse problem domains. However, existing benchmarks primarily focus on assessing factual and logical correctness in downstream tasks, with limited emphasis on evaluating MLLMs' ability to interpret pragmatic cues and intermodal relationships. To address this gap, we assess the competency of MLLMs in performing Multimodal Discourse Analysis (MDA) using Coherence Relations. Our benchmark, CORDIAL, encompasses a broad spectrum of Coherence Relations across 3 different discourse domains at varying levels of granularity. Through our experiments on 10+ MLLMs employing different prompting strategies, we show that even top models like Gemini 1.5 Pro and GPT-4o fail to match the performance of simple classifier-based baselines. This study emphasizes the need to move beyond similarity-based metrics and adopt a discourse-driven framework for evaluating MLLMs, providing a more nuanced assessment of their capabilities. The benchmark and code are available at: https://aashish2000.github.io/CORDIAL/.

Downloads

Next from ACL 2025

Adversarial Alignment with Anchor Dragging Drift (A3D2): Multimodal Domain Adaptation with Partially Shifted Modalities

Similar lecture

ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models