United States

Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specific harmful parameters, current methods remain vulnerable to diverse jailbreaks. We first conduct an empirical study and discover that this failure mechanism is caused by jailbreaks primarily activating non-erased parameters in the intermediate layers. Further, by probing the underlying mechanism through which these circumvented parameters reassemble into the prohibited output, we verify the persistent existence of dynamic **jailbreak paths** and show that the inability to rectify them constitutes the fundamental gap in existing unlearning defenses. To bridge this gap, we propose **J**ailbreak **P**ath **U**nlearning (JPU), which is the first to rectify dynamic jailbreak paths towards safety anchors by dynamically mining on-policy adversarial samples to expose vulnerabilities and identify jailbreak paths. Extensive experiments demonstrate that JPU significantly enhances jailbreak resistance against dynamic attacks while preserving the model&#39;s utility.

ACL 2026

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification

### 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)

Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specific harmful parameters, current methods remain vulnerable to diverse jailbreaks. We first conduct an empirical study and discover that this failure mechanism is caused by jailbreaks primarily activating non-erased parameters in the intermediate layers. Further, by probing the underlying mechanism through which these circumvented parameters reassemble into the prohibited output, we verify the persistent existence of dynamic **jailbreak paths** and show that the inability to rectify them constitutes the fundamental gap in existing unlearning defenses. To bridge this gap, we propose **J**ailbreak **P**ath **U**nlearning (JPU), which is the first to rectify dynamic jailbreak paths towards safety anchors by dynamically mining on-policy adversarial samples to expose vulnerabilities and identify jailbreak paths. Extensive experiments demonstrate that JPU significantly enhances jailbreak resistance against dynamic attacks while preserving the model's utility.

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.

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.

Despite substantial advances in large language models (LLMs), producing factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucination and the limitations of LLMs in bridging long-tail knowledge gaps. To address this, we propose AMATA, an Adaptive Multi-Agent Trajectory Alignment framework that dynamically integrates external knowledge to improve response interpretability and factual grounding. Our architecture leverages six specialized agents that collaboratively perform structured actions for complex question reasoning. We formalize multi-agent collaboration with external tools as a trajectory preference alignment problem, incorporating question-aware agent customization and inter-agent preference harmonization. AMATA introduces two principal innovations: (1) Intra-Trajectory Preference Learning, which learns objective-oriented preferences to prioritize critical agents, and (2) Inter-Agent Dependency Learning, which captures cross-agent tool dependencies through a novel dependency-aware direct preference optimization technique. Empirical results show that AMATA consistently outperforms baseline approaches, knowledge-augmented frameworks, and LLM-based trajectory systems on five established knowledge-intensive QA benchmarks. Further analysis demonstrates the efficiency of our method in reducing token consumption.

AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering

Large language models (LLMs) have been applied to sequential decision-making tasks like multi-armed bandits (MAB), where an LLM is tasked with selecting arms in each iteration. However, this direct arm selection approach is often suboptimal. We propose an alternative method combining classical MAB algorithms with LLMs. Specifically, we use a classical MAB framework and leverage the in-context learning capability of LLMs for reward prediction. First, we integrate the LLM-based predictor into Thompson sampling (TS) with a decaying temperature schedule to balance exploration and exploitation. We also incorporate the predictor into a regression oracle-based MAB algorithm with explicit exploration. Additionally, we extend our TS-based algorithm to dueling bandits, where only preference feedback between arm pairs is available, requiring significant algorithmic modifications. Our empirical evaluations on synthetic MAB tasks show that our algorithms outperform LLM-based direct arm selection. In experiments on real-world text datasets, we demonstrate that, in tasks where arms lack exploitable semantic meaning, our approach delivers significantly better performance than direct arm selection.

Large Language Model-Enhanced Multi-Armed Bandits

Recent advancements in LLM-based multi-agent systems have demonstrated remarkable collaborative capabilities across complex tasks. To enhance the overall efficiency, existing methods often rely on aggressive graph topology evolution for agents (e.g., node or edge pruning), which risks prematurely discarding valuable agents due to transient issues such as hallucinations or temporary knowledge gaps. However, such hard pruning overlooks the potential for "zombie" agents to recover and contribute in subsequent discussion rounds. In this paper, we propose AgentRevive, a Markov state-aware framework for resilient multi-agent evolution. Our approach dynamically manages agent collaboration through soft state transitions, implemented via two key components: (1) State-Aware Policy Learning: Agent states are divided into "Active", "Standby", and "Terminated", selectively propagating messages based on agent memory. The policy employs a risk estimator to optimize agent state transitions by assessing hallucination risk, minimizing the influence of unreliable nodes while safeguarding valuable ones. (2) State-Aware Edge Optimization: Subgraph edges are pruned according to states learned from the policy, permanently removing "Terminated" nodes and retaining "Standby" nodes for subsequent rounds to observe potential future contributions. Extensive experiments on general reasoning, domain-specific, and hallucination challenge tasks show that our method consistently outperforms strong baselines and significantly reduces token consumption through state-aware agent scheduling.

Taming "Zombie" Agents: A Markov State-Aware Framework for Resilient Multi-Agent Evolution

Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs, enabling the selection of the best-performing LLMs for specific user queries while balancing performance and cost. However, current routing approaches often face limitations in scalability when dealing with a large pool of specialized LLMs, or in their adaptability to extending model scope and evolving capability domains. To overcome those challenges, we propose **InferenceDynamics**, a flexible and scalable multi-dimensional routing framework by modeling the capability and knowledge of models. We operate it on our comprehensive dataset **RouteMix**, and demonstrate its effectiveness and generalizability in group-level routing using modern benchmarks including MMLU-Pro, GPQA, BigGenBench, and LiveBench, showcasing its ability to identify and leverage top-performing models for given tasks, leading to superior outcomes with cost efficiency. The broader adoption of InferenceDynamics can empower users to harness the full specialized potential of the LLM ecosystem, and our code will be made publicly available to encourage further research.

InferenceDynamics: Adaptive LLM Routing through Structured Capability and Knowledge Profiling

Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis under escalating pressure. We propose \textbf{\textsc{Med-Stress}}, a targeted stress test framework that evaluates belief stability under escalating pressure. Across nine frontier large language models (LLMs), we find a clear dissociation between medical knowledge and robustness: high initial diagnostic capability does not imply high belief stability, yielding large knowledge-robustness gaps for several LLMs. To mitigate this failure mode, we propose a lightweight inference-time defense, \textbf{\texttt{RBED}} (\textbf{R}ole-\textbf{B}ased \textbf{E}pistemic \textbf{D}efense), and \textbf{\texttt{R-FT}} (\textbf{R}esilience-oriented \textbf{F}ine-\textbf{T}uning), a training-time approach that internalizes evidence-based resistance to pressure. Experiments show that \textbf{\texttt{R-FT}} nearly eliminates belief change and substantially improves robustness.

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure

Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning (VAR), a reinforcement learning framework that reformulates reasoning as a hierarchical search with self-verification. VAR enforces traceable evidence grounding by generating explicit bounding boxes, guided by a novel reward function combining geometric precision and semantic sufficiency. Furthermore, it replaces linear Chain-of-Thought with a tree-search policy capable of backtracking to correct logical errors. Theoretical analysis validates the framework's reliability, and extensive experiments demonstrate that VAR significantly outperforms state-of-the-art methods on complex hallucination and safety benchmarks.

Visual Attention Reasoning via Hierarchical Search and Self-Verification

Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with music and speech often developed in isolation, hindering progress towards universal audio synthesis. This separation stems from inherent task conflicts between semantic speech and structural music modeling, and severe data imbalances, which impede the development of a truly unified model. To address these challenges, we propose **UniMoE-Audio**, a unified speech and music generation model built upon a novel **D**ynamic-**C**apacity **M**ix-**o**f-**E**xperts (DCMoE) framework. Architecturally, UniMoE-Audio extends the conventional MoE paradigm by introducing a Top-$P$ routing strategy for adaptive capacity allocation. To tackle data imbalance, we introduce a three-stage training curriculum: 1) Independent Specialist Training leverages original datasets to instill domain-specific knowledge into each specialists without interference; 2) MoE Integration and Warmup incorporates these specialists into the UniMoE-Audio architecture, warming up the gate module and shared expert using a subset of balanced dataset; and 3) Synergistic Joint Training trains the entire model end-to-end on the fully balanced dataset, fostering enhanced cross-domain synergy. Extensive experiments show that UniMoE-Audio not only achieves state-of-the-art performance on major speech and music generation benchmarks, but also demonstrates superior synergistic learning, mitigating the performance degradation typically seen in naive joint training. Our findings highlight the substantial potential of specialized MoE architecture and curated training strategies in advancing universal audio generation.

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts

Omni-modal large language models (OLLMs) offer a promising end-to-end solution for slide-enhanced speech recognition due to their inherent multimodal capabilities. However, we found a fundamental issue faced by OLLMs: \textit{Visual Interference}, where models show a bias towards visible text over auditory signals, causing them to hallucinate slide content that was never spoken. To address this, we propose Visually-Anchored Policy Optimization (VAPO), which aims to reshape models' inference process to follow the human-like ``Look-then-Listen'' inference chain. Specifically, we design a temporally decoupled policy: the model first extracts visual priors in a \<think> block to serve as semantic anchors, then generates the transcription in an \<answer> block. The policy is optimized via multi-objective reinforcement learning. Furthermore, we introduce SlideASR-Bench, a comprehensive benchmark designed to address the scarcity of entity-rich data, comprising a large-scale synthetic corpus for training and a challenging real-world test set for evaluation. We conduct extensive evaluations demonstrating that VAPO effectively eliminates visual interference and achieves state-of-the-art performance on SlideASR-Bench and public datasets, significantly reducing entity recognition errors in specialized domains.

VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models

Hausa texts are often characterized by writing anomalies such as incorrect character substitutions and spacing errors, which sometimes hinder natural language processing (NLP) applications. This paper presents an approach to automatically correct the anomalies by finetuning transformer-based models. Using a corpus gathered from several public sources, we create a large-scale parallel dataset of over 400,000 noisy-clean Hausa sentence pairs by introducing synthetically generated noise to mimic realistic writing errors. Moreover, we finetune several multilingual and African language models, including M2M100, AfriTeVA, NCAIR1/N-ATLaS, UBC-NLP/cheetah-base, and other variants of BART and T5 for this correction task. Our experimental results demonstrate that models such as M2M100 achieve state-of-the-art results despite their smaller size and distinct pretraining, and that correcting errors can have a significant impact in improving downstream tasks such as text classification, machine translation, question answering, and LLM prompting in general. This research provides a methodology, a publicly available dataset, and a comparison of models to improve Hausa text quality, thereby advancing NLP capabilities for the language and offering transferable insights for other low-resource languages.

Automatic Correction of Writing Anomalies in Hausa Texts

Recent advancements in Large Reasoning Models (LRMs) have showcased strong performance across various reasoning tasks by leveraging System‑2 thinking capabilities. However, existing studies indicate that this reasoning ability alone does not reliably transfer to the general alignment domain. Inspired by cognitive science and how humans solve tasks, we argue that LRMs must be equipped with metacognitive knowledge to fully utilize their System‑2 capabilities. In this paper, we propose Priority‑Aware Metacognition (PAM), which guides the model to first identify the top‑level human preference (e.g., harmlessness) as a means of understanding the alignment task’s nature, and then apply other kinds of metacognitive knowledge to better monitor and regulate the model's thinking process. We implement PAM via a two-stage pipeline: a cold-start phase that collects structured metacognitive knowledge based on Flavell’s theoretical framework, and a preference-optimization phase that further reinforces such metacognition. Extensive experiments validate the effectiveness of PAM. Under the same training pipelines, PAM consistently yields higher performance, improving general domain alignment performance by \textasciitilde 10 points on the helpfulness and harmless benchmarks. Code is available at https://anonymous.4open.science/r/PAM-RM-02DF.

Downloads

Next from ACL 2026

AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering

Similar lecture

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs