United States

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in solving complex mathematical problems. Recent studies show that distilling long reasoning trajectories can effectively enhance the reasoning performance of small-scale student models. However, teacher-generated reasoning trajectories are often excessively long and structurally complex, making them difficult for student models to learn. This mismatch leads to a gap between the provided supervision signal and the learning capacity of the student model. To address this challenge, we propose Prefix-ALIGNment distillation (P-ALIGN), a framework that fully exploits teacher CoTs for distillation through adaptive prefix alignment. Specifically, P-ALIGN adaptively truncates teacher-generated reasoning trajectories by determining whether the remaining suffix is concise and sufficient to guide the student model. Then, P-ALIGN leverages the teacher-generated prefix to supervise the student model, encouraging effective prefix alignment. Experiments on multiple mathematical reasoning benchmarks demonstrate that P-ALIGN outperforms all baselines by over 3%. Further analysis indicates that the prefixes constructed by P-ALIGN provide more effective supervision signals, while avoiding the negative impact of redundant and uncertain reasoning components. All codes are available at https://github.com/NEUIR/P-ALIGN.

ACL 2026

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment

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. <br>
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) <br><br><br>
<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>
<br><br><br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>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.

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.

technical paper

Large language models (LLMs) perform well on Standard Chinese but struggle with low-resource Chinese dialects due to substantial phonological divergence. We investigate whether incorporating Middle Chinese, the common historical ancestor of most of the modern Chinese dialects, can improve dialectal pronunciation modeling in a linguistically interpretable manner. We focus on two specific task variants: (1) conditional sound change rule induction (a variant of Sound Law Induction, SLI), where models infer executable phonological transformation rules from Middle Chinese to modern dialects, and (2) sentence-level dialectal pronunciation transcription (a variant of Grapheme-to-Phoneme, G2P), requiring dialect-specific International Phonetic Alphabet (IPA) generation. We construct a multi-source dataset covering Middle Chinese and 12 modern Chinese dialects, including character-level correspondences, rule exemplars, and sentence-level IPA transcription. We adopt a parameter-efficient training framework combining LoRA-based supervised fine-tuning and reinforcement learning via Group Relative Policy Optimization (GRPO) for the first task. Across both tasks and a wide range of dialects and evaluation metrics, our approach achieves overall improvements over strong baselines, including DeepSeek-V3.2 and ChatGPT-5.2, while revealing variation across dialects. These results demonstrate the value of leveraging historical linguistic knowledge for modeling low-resource Chinese dialects.

Would LLMs be Good Historical Linguists and Chinese Dialect Learners?

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer from slow convergence due to gradient conflict between adversarial objectives and the model's safety-retrieval mechanism. We propose Attention-Guided Visual Jailbreaking, which circumvents rather than overpowers safety alignment by directly manipulating attention patterns. Our method introduces two simple auxiliary objectives: (1) suppressing attention to system-prompt tokens and (2) anchoring generation on adversarial image features. This simple yet effective push-pull formulation reduces gradient conflict by 45% and achieves 94.4% attack success rate on Qwen-VL (vs. 68.8% baseline) with 40% fewer iterations. At tighter perturbation budgets ($\epsilon=8/255$), we maintain 59.0% ASR compared to 45.7% for standard methods. Mechanistic analysis reveals a failure mode we term safety blindness: successful attacks suppress system-prompt attention by 80%, causing models to generate harmful content not by overriding safety rules, but by failing to retrieve them.

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking

While Large Language Models have significantly advanced Text2SQL generation, a critical semantic gap persists: syntactically valid queries can still misinterpret user intent. To mitigate this challenge, we propose GBV-SQL, a multi-agent framework that introduces Guided Generation with SQL2Text Back-translation Validation. In particular, a dedicated validator translates generated SQL back into natural language and checks whether its logic is aligned with the original question. Beyond the method itself, we also conduct a systematic audit of benchmark quality and introduce a typology of ``Gold Errors'' in Text2SQL datasets. Our analysis shows that benchmark issues can coexist with strong execution accuracy and can substantially affect evaluation outcomes. On the challenging BIRD benchmark, GBV-SQL achieves 63.23% execution accuracy, a 5.8% absolute improvement over the Deepseek-v3-based MAC-SQL setting. Under manually audited benchmark corrections, GBV-SQL reaches 96.5% (dev) and 97.6% (test) on Spider, and 90.42% on repaired BIRD dev, providing a diagnostic view of model behavior under improved gold quality. Our work contributes both a practical framework for semantic validation and an empirical analysis of benchmark integrity in Text2SQL evaluation.

GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL

Simulating student writing behavior offers a promising pathway to scalable feedback evaluation and teacher training. However, existing LLM-based approaches tend to model overly capable learners who readily understand and over-apply feedback, resulting in pedagogically implausible behavior. In this work, we introduce pedagogical realism as a guiding principle for student writing simulation, emphasizing bounded cognition, selective feedback comprehension, and developmentally plausible learning processes. To operationalize this idea, we propose CPT-Agent, a cognitively grounded framework that decouples cognitive ability from writing proficiency and models their interaction during writing and revision. CPT-Agent combines probabilistic modeling of cognitive development, proficiency-controlled text generation, and structured memory for skill accumulation. Experiments show that it (1) produces clearly distinguishable proficiency levels, (2) generates cognitively plausible revisions consistent with instructional theories, and (3) achieves strong agreement with expert judgments in evaluating feedback quality. These results highlight the importance of modeling cognitive constraints in LLM-based student simulation and demonstrate the potential of pedagogically realistic agents for automated feedback assessment and teacher development.

CPT-Agent: A Cognitive Process Theory-driven Framework for Student Simulation in Writing Development

Search agents have emerged as a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. However, training these agents via Reinforcement Learning (RL) faces a critical dilemma: interacting with live commercial Web APIs is prohibitively expensive, while relying on static data snapshots often introduces noise due to data misalignment. This misalignment generates corrupted reward signals that destabilize training by penalizing correct reasoning or rewarding hallucination. To address this, we propose SearchGym, a simulation environment designed to bootstrap robust search agents. SearchGym employs a rigorous generative pipeline to construct a verifiable knowledge graph and an aligned document corpus, ensuring that every reasoning task is factually grounded and strictly solvable. Building on this controllable environment, we introduce SearchGym-RL, a curriculum learning methodology that progressively optimizes agent policies through purified feedback, evolving from basic interactions to complex, long-horizon planning. Extensive experiments across the Llama and Qwen families demonstrate strong Sim-to-Real generalization. Notably, our Qwen2.5-7B-Base model trained within SearchGym surpasses the web-enhanced ASearcher baseline across nine diverse benchmarks by an average relative margin of 10.6\%. Our results validate that high-fidelity simulation serves as a scalable and highly cost-effective methodology for developing capable search agents.

SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation

Empathy relies on the cognitive capacity to relate to similar past experiences. Consequently, retrieval-based approaches utilize analogous exemplars to guide empathetic dialogue generation. However, existing methods prioritize semantic similarity over emotion characteristics, often leading to unempathetic responses. To address this, we propose REG, a framework that integrates four Emotion Attributes into the retrieval process to ensure explicit emotional alignment. Furthermore, to mitigate the noise and limited diversity caused by coarse-grained sentence-level attributes, we incorporate Token-level Retrieval for finer granularity and a Retrieval Candidate Augmentation strategy to enhance diversity. Empirical results on the EmpatheticDialogues dataset demonstrate that REG significantly outperforms baselines, offering a robust solution for empathetic generation.

REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation

Reading order detection is the foundation of document understanding.
Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we challenge this assumption by revealing a critical flaw: Positional Disparity, a phenomenon where models demonstrate mastery over the deterministic start and end regions but suffer a performance collapse in the complex intermediate sections.
This degradation arises because standard training allows the massive volume of easy patterns to drown out the learning signals from difficult layouts.
To address this, we propose FocalOrder, a framework driven by Focal Preference Optimization (FPO).
Specifically, FocalOrder employs adaptive difficulty discovery with exponential moving average mechanism to dynamically pinpoint hard-to-learn transitions, while introducing a difficulty-calibrated pairwise ranking objective to enforce global logical consistency.
Extensive experiments demonstrate that FocalOrder establishes new state-of-the-art results on OmniDocBench v1.0 and Comp-HRDoc.
Our compact model not only outperforms competitive specialized baselines but also significantly surpasses large-scale general VLMs.
These results demonstrate that aligning the optimization with intrinsic structural ambiguity of documents is critical for mastering complex document structures.

FocalOrder: Focal Preference Optimization for Reading Order Detection

Document-level Event Causality Identification (DECI) aims to identify causal relations among multiple events within unstructured text. Existing methods predominantly rely on local semantic similarity for independent event-pair discrimination, thereby overlooking the influence of the overall narrative backbone in the propagation of causal dependencies and the role differentiation of events within multi-cause/multi-effect structures. Therefore, we propose a suggest-verify-revise approach for document-level Event Causality Identification with narrative consistency (SVRECI). In the suggest stage, we integrate multi-dimensional heuristic causal suggestions generated by an LLM with structural suggestions derived from hypergraph modeling to provide multi-source initial support for candidate event pairs. In the verify stage, we introduce a Topological Hawkes process to perform constrained verification of narrative propagation consistency among events. In the revise stage, we construct a dynamically evolving document-level causal graph and incorporate a structure-aware dual-level contrastive learning mechanism at both the event and event-pair levels, iteratively reducing noisy edges over multiple iterations. Experimental results on EventStoryLine and Causal-TimeBank datasets demonstrate that our approach outperforms previous methods.

Suggest-Verify-Revise: A Three-Stage Document-Level Event Causality Identification with Narrative Consistency

Large reasoning models (LRMs) achieve strong performance on complex tasks by generating intermediate reasoning before the final answer, yet they remain prone to reasoning hallucinations such as subtle arithmetic or constraint-violation errors. Prior hallucination detectors often rely on external verification or local token-level signals, which are limited for LRMs and largely overlook whether the cross-phase information flow from reasoning to answering is structurally robust. We propose Routing Focus Score (RFS), a step-level indicator that measures how strongly cross-step attention routing aligns with semantic proximity derived from hidden-state cosine similarity. We further design RFS-Guard, a lightweight hallucination detection framework based on RFS. Empirically, we observe that higher reasoning–answer RFS is consistently associated with higher hallucination risk, suggesting a routing-collapse failure mode where models might prefer self-confirmation loops and suppress the ability to audit their own generations. Experimental results across multiple domains and models demonstrate the superiority of RFS-Guard for detecting and localizing hallucinations in LRMs without requiring external tools or repeated sampling.

RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models

Retrieval-augmented generation (RAG) is a widely adopted paradigm for enhancing LLMs in medical applications by incorporating expert multi-modal knowledge during generation. However, the underlying retrieval databases may naturally contain, or be intentionally injected with, adversarial knowledge, which can perturb model outputs and undermine system reliability. To investigate this risk, prior studies have explored knowledge poisoning attacks in medical RAG systems. Nevertheless, most of them rely on the strong assumption that adversaries possess prior knowledge of user queries, which is unrealistic in deployments and substantially limits their practical applicability. In this paper, we propose M$^3$Att, a knowledge-poisoning framework designed for medical multimodal RAG systems, assuming only limited distribution knowledge of the underlying database. Our core idea is to inject covert misinformation into textual data while using paired visual data as a query-agnostic trigger to promote retrieval. We first propose a unified framework that introduces imperceptible perturbations to visual inputs to manipulate retrieval probabilities. Besides, due to the prior medical knowledge in LLMs, naively poisoned medical content with explicit factual errors can be corrected during generation. Thus, we leverage the inherent ambiguity of medical diagnosis and design a covert misinformation injection strategy that degrades diagnostic accuracy while evading model self-correction. Experiments on five LLMs and datasets demonstrate that M$^3$Att consistently produces clinically plausible yet incorrect generations. Codes: \url{https://anonymous.4open.science/r/M3Att}.

Downloads

Next from ACL 2026

Would LLMs be Good Historical Linguists and Chinese Dialect Learners?

Similar lecture

MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision