United States

This paper proposes shortcut decoding, an efficient framework for accelerating Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs). Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. Motivated by the observation that LLMs frequently converge to correct solutions internally before completing explicit textual reasoning, we propose a dual-signal adaptive controller that integrates lightweight probes over internal hidden states with step-level entropy. This controller detects convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness. Experiments across multiple mathematical reasoning benchmarks demonstrate that shortcut decoding reduces token usage by approximately 35%, maintains accuracy comparable to full CoT decoding, and achieves final-answer accuracy comparable to the full CoT baseline, outperforming existing early-stopping methods without updating the base model. Our code is available at https://github.com/kuromi9527/shortcut_decoding.

ACL 2026

Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding

### 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.

Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving pseudo-rewards from majority voting consensus.
However, existing TTRL methods rely exclusively on positive pseudo-labeling strategies.
Such reliance becomes vulnerable under challenging scenarios where answer distributions are highly dispersed, resulting in weak consensus that inadvertently reinforces incorrect trajectories as supervision signals.
In this paper, we propose SCRL (Selective-Complementary Reinforcement Learning), a robust test-time reinforcement learning framework that effectively mitigates label noise amplification.
SCRL develops Selective Positive Pseudo-Labeling, which enforces strict consensus criteria to filter unreliable majorities. 
Complementarily, SCRL introduces Entropy-Gated Negative Pseudo-Labeling, the first negative supervision mechanism in TTRL, to reliably prune incorrect trajectories based on generation uncertainty. 
Extensive experiments on mathematical reasoning benchmarks demonstrate that SCRL achieves substantial improvements over baselines, while maintaining robust generalization and training stability under constrained rollout budgets.

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

Social bot accounts have long been disseminating disinformation and engaging in malicious activities on social media platforms. Detecting these social bots has become a critical and urgent task, essential for maintaining a healthy online ecosystem. Existing social bot detection research usually provides detection results directly without corresponding supportive explanations, making it difficult to assess the extent to which such predictions are trustworthy. This is a key concern for online moderation. In this work, we explore the detection interpretation and summarize a four-dimensional clue framework from individual and social perspectives. We propose CDRBot, which primarily employs outcome-reward reinforcement learning to train inspectors to generate faithful, grounded, and readable clues from the *User Information*, *Semantic Features*, *Interactive Situation*, and *Behavioral Pattern*. These clues are then integrated to make final predictions. Experimental results demonstrate that our approach outperforms other baselines in detection performance. The generated clues are faithful, grounded, and readable, and can significantly enhance the performance of large language models in social bot detection.

Exploring and Distilling Multi-Dimensional Clues for Interpretable Social Bot Detection

The rapid advancement of large language models (LLMs) has driven the deployment of LLM-based AI tutors on online learning platforms. This widespread adoption highlights an urgent need for systematic benchmarks to evaluate their tutoring capabilities. However, existing evaluations predominantly focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning. To bridge this gap, we introduce LongTutor, a benchmark for long-term personalized tutoring grounded in formative assessment theory. Built from expert-annotated real-world learning logs, LongTutor evaluates LLMs across three progressive tasks: historical evidence acquisition, knowledge state diagnosis, and adaptive teaching action. Our experiments reveal a critical capability mismatch: while LLMs excel at evidence acquisition, they struggle to effectively leverage long-term history for accurate diagnosis and adaptive teaching. To enable scalable benchmark expansion, we further propose an automated generator–verifier pipeline, paving the way toward truly long-term AI tutoring systems.

LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring

Currently, large language models (LLMs) have significant limitations in spatial reasoning, particularly in the absence of visual input. To address this issue, we introduce SODA (Spatial OODA), which draws inspiration from the OODA cognitive loop (Observe, Orient, Decide, Act), originally designed to enhance human decision-making in dynamic environments. Specifically, we embed the OODA loop into multiple control tasks, generating the SPOD-143k dataset, and successfully integrate it into LLMs through a two-phase and spatia-aware training strategy (SFT and GRPO). Furthermore, to fill the gap in evaluating spatial reasoning in purely text-based LLMs, we introduce the SPOD-Bench benchmark, including multiple tasks divided into three levels of difficulty. Experimental results show that SODA significantly enhances the spatial reasoning capabilities of LLMs across testing scenarios including SPOD-Bench, SPACE and applications, providing a replicable and effective paradigm for improving the spatial cognition of LLMs.

One Cognitive Loop Is Enough: SODA unlocks Pure-Text Spatial Reasoning in Large Language Models

Large language models (LLMs) have remarkable capabilities, but adapting them to specialized domains poses a fundamental question: \textit{how should accumulated experience be represented and leveraged?} Existing approaches represent experience either as explicit textual artifacts in prompts (\textit{e.g.}, retrieved documents or dialogues) or implicitly within model weights via fine-tuning (\textit{e.g.}, LoRA adapters). However, textual methods are limited by context windows and cannot internalize knowledge, while parametric fine-tuning yields one adapter per task with minimal cross-task skill reuse. We propose \textbf{ReX} (\textbf{Re}usable e\textbf{X}perience), an experience-centric adaptation framework that treats latent experiences — recurring reasoning patterns and skills — as fundamental units for LLM specialization. Our method learns a shared Experience Bank of foundational skill vectors and uses a VAE-based encoder to map each input to a low-dimensional experience code. An Experience Router then dynamically composes the relevant skill vectors from this bank into a lightweight adapter for that input. By reusing skills across inputs, \textbf{ReX} enables implicit knowledge sharing across tasks without any explicit task identifiers. Experiments on multi-task NLP benchmarks show that this approach outperforms standard task-specific fine-tuning, yielding improved generalization through flexible skill reuse. Code is available at \url{https://github.com/iLearn-Lab/ACL26-ReX}.

Reusable Experiences: Latent Routing and Modular Composition in LLMs

Large language models (LLMs) have achieved remarkable performance across diverse tasks, largely driven by large-scale pretraining. However, this data abundance introduces test data contamination, where benchmark datasets overlap with pretraining corpora, undermining the reliability of model evaluation by confounding memorization with genuine generalization. To mitigate this issue, existing training data detectors attempt to identify clean (unseen) samples from contaminated test sets, but often suffer from residual contamination due to the black-box nature of LLMs. As a result, contaminated data may be mistakenly retained, leading to unreliable evaluation.To address this challenge, we propose FTD (FDR-controlled Training Data detection), a principled framework that detects and filters contaminated evaluation data while providing a statistical guarantee: the proportion of contaminated samples mistakenly retained as clean, the false discovery rate (FDR), is provably controlled below a user-specified threshold. FTD combines multiple complementary detectors via an adaptive weighting strategy, and we theoretically show it achieves high statistical power under valid FDR control. Extensive experiments on real-world benchmarks demonstrate that FTD significantly reduces residual contamination compared to existing methods while preserving evaluation consistency.

Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees

Low-resource multilingual OCR faces a dual challenge: complex script structures and severe data scarcity. In such settings, existing OCR models often struggle, as coarse visual representations combined with weak linguistic priors lead to frequent errors among visually similar characters.
To address this, we present BASA (Beyond Atomic Sub-character Alignment), a OCR framework built upon high-resolution visual and language backbones with a novel glyph-aware interface. The core technical contribution is the Glyph-Aware Fine-grained Adapter (GAFA). Unlike standard linear projectors, GAFA employs learnable glyph prototypes to actively align sub-character structural primitives (e.g., strokes and radicals) with visual features, explicitly resolving topological ambiguities during vision–language alignment. To complement this, we introduce a two-stage curriculum learning strategy supported by a Glyph-Aware Reverse Synthesis pipeline, which generates large-scale multilingual training corpora with automatic, zero-cost component labels. Furthermore, we construct BASA-Bench, a representative benchmark spanning 11 languages with diverse script structures and 23 authentic scenarios. Experiments demonstrate that BASA achieves consistent improvements over strong OCR baselines, particularly on scripts with complex compositions. Our model and benchmark will be available at \url{https://github.com/NcutLLM/BASA}.

Beyond Atomic Characters: Glyph-Aware Sub-character Alignment for Low-Resource Multilingual OCR

With the rapid advancement of large language models (LLMs), automated code generation has made remarkable progress. Recent studies explore multi-agent collaboration and adopt planning–coding–debugging workflows to enhance performance. However, these approaches are constrained by rigid, predefined workflows that fail to flexibly adjust their plans and lack effective verification of intermediate reasoning steps. In this work, we propose MavenCoder, a model-adaptive and verification–enhanced framework for competition-level code generation. MavenCoder leverages adaptive assessment aligned with the model’s capabilities to select planning strategies, while providing timely feedback and correction via multi-perspective verification. This adaptive problem-solving paradigm mitigates earlier limitations by enabling flexible planning and timely error correction. Compared with existing state-of-the-art approaches, MavenCoder achieves superior pass@1 results across multiple benchmarks, achieving 87.5% on LiveCodeBench, 93.9% on HumanEval+, 81.7% on MBPP+, and 46.1% on CodeContests, outperforming recent agent-based systems with improvement exceeding 3%--40%.

MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement

Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation. To address this, we introduce \textbf{Forgery Attribution Report Generation}, a new multimodal task designed to provide post-hoc forensic evidence for manipulated images. This task jointly localizes forged regions (``Where``) and generates natural language explanations grounded in the editing process (``Why``). This dual-focus approach goes beyond traditional binary forensics, providing a comprehensive, interpretable understanding of the manipulation. To enable research in this domain, we present \textbf{Multi-Modal Tamper Tracing (MMTT)}, a large-scale dataset of 152,217 samples. Each sample features a process-derived ground-truth mask and a human-authored textual description, ensuring high annotation precision and linguistic richness. We further propose \textbf{ForgeryTalker}, a unified end-to-end baseline that integrates vision and language via a shared encoder and dual decoders for mask and text generation. Experiments show that ForgeryTalker achieves competitive performance on both subtasks, i.e., 59.3 CIDEr and 73.67 IoU, establishing a strong baseline for explainable multimedia forensics. Our dataset and code are available at: https://github.com/NattyLianJc/Generating-Attribution-Reports.

Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline

Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical tasks, detecting malicious agents has become a critical security concern. Although existing graph anomaly detection (GAD)-based defenses can identify anomalous agents, they mainly rely on coarse sentence-level information and overlook fine-grained lexical cues, leading to suboptimal performance. Moreover, the lack of interpretability in these methods limits their reliability and real-world applicability. To address these limitations, we propose \ourmethod, an explainable and fine-grained safeguarding framework for detecting malicious agents in MAS. To incorporate both coarse and fine-grained textual information for anomalous agent identification, we utilize a bi-level agent encoder to jointly model the sentence- and token-level representations of each agent. A theme-based anomaly detector further captures the evolving discussion focus in MAS dialogues, while a bi-level score fusion mechanism quantifies token-level contributions for explanation. Extensive experiments across diverse MAS topologies and attack scenarios demonstrate robust detection performance and strong interpretability of XG-Guard.

Downloads

Next from ACL 2026

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time

Similar lecture

“Well, Keep Thinking”: Enhancing LLM Reasoning with Adaptive Injection Decoding