United States

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves consistently high attack success rates across models by exploiting the model&#39;s own ethical reasoning to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility.

ACL 2026

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs

PERC 2022 is focused on "queering physics education" through an intersectional lens. By "queering," we are centering queer theory which breaks down social constructions and hierarchies to unpack normalized assumptions. In the context of physics education, we want to apply the theory to unpack who has power in physics to control the production of future physicists, how physics policies and practices are sometimes built on ideas of punishment and power, and how PER embeds binaries in both its content and sociological research. Further, we want to encourage a dialogue that is both a critique and an imagining of a queer future for PER.

Explicit attention will be given to constructions of race, (dis)ability, gender, sexuality and how they interact and impact lived experiences.

We have had such a fun time organizing this year’s PERC. You might be aware that we were committed to transparency and documenting our processes and decision making which we outlined here. This year has also been challenging to be a queer or otherwise marginalized person in the US. And we continue to seek and provide support for those individuals.

As such, we recommend that folks visiting Grand Rapids who have the means consider giving to some local organizations who are working to advocate for those impacted by historic and ongoing marginalization and violence.


PERC SM 22

PERC 2022 focused on "queering physics education" through an intersectional lens. By "queering," we centered queer theory which breaks down social constructions and hierarchies to unpack normalized assumptions. In the context of physics education, we apply the theory to unpack who has power in physics to control the production of future physicists, how physics policies and practices are sometimes built on ideas of punishment and power, and how PER embeds binaries in both its content and sociological research. Further, we wanted to encourage a dialogue that is both a critique and an imagining of a queer future for PER. Explicit attention was given to constructions of race, (dis)ability, gender, sexuality and how they interact and impact lived experiences.

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves consistently high attack success rates across models by exploiting the model's own ethical reasoning to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model 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. <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.

**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.

High-stakes domains such as finance, law, and biomedicine demand both accurate results and rigorous reasoning. Current reinforcement learning paradigms primarily rely on outcome-based rewards, often overlooking latent logical fallacies in intermediate steps. Leveraging the cognitive asymmetry where falsifying local errors is more efficient than generating global correctness, we propose RADO (Reasoning Audit-Driven Optimization). RADO introduces a specialized audit model augmented with external tools to identify local logical ruptures and calibrate reward signals. By integrating Direct Preference Optimization (DPO) with Group Relative Policy Optimization (GRPO), our framework enables explicit supervision over reasoning paths. Experimental results demonstrate that RADO consistently improves final accuracy while significantly enhancing logical rigor in high-stakes domains.

RADO: Reasoning Audit-Driven Optimization for Rigorous Reasoning in High-Stakes Domains

Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consuming the majority of computational resources. 
While Mixture-of-Experts (MoE) architectures can reduce this cost through sparse activation, restructuring existing dense models into MoEs typically requires extensive retraining on hundreds of billions of tokens.
We propose an analytical post-training framework that rapidly restructures FFNs into sparse MoE architectures using only a small calibration dataset. 
The method analyzes neuron activation patterns to partition neurons into always-active shared experts and conditionally activated routed experts, then constructs a router analytically from representative neuron statistics, enabling immediate deployment or optional lightweight fine-tuning. 
This approach applies both to dense models and recursively to existing MoE models for hierarchical sparsity.
Experiments demonstrate up to $1.17\times$ speedup in compute-bound scenarios with only minutes of processing and 2k-sample fine-tuning, outperforming methods requiring orders of magnitude more resources.

Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis

Computational argumentation has received increasing attention in recent years. However, existing debate datasets neglect some important labels for argument mining, generation, and evaluation. Meanwhile, the lack of comprehensively annotated Chinese oral debate datasets hinders progress in this field. To address these gaps, we introduce a comprehensive Chinese Evaluation Dataset for Computational Argumentation, named CEDAR. Compared to previous datasets, CEDAR includes the essential labels of computational argumentation (claim, stance, evidence) and five additional crucial labels: rhetorical figures, debater roles, modal words, utterance time, and debate results. Moreover, it offers complete transcripts of each debate, including speeches from the Pro and Con sides. Thus, the proposed CEDAR not only supports common argument mining and generation tasks, but also provides resources for rhetorical figure detection, argument quality evaluation, and debate result prediction. This dataset covers 600 debates about 318 topics from Chinese debate competitions. Besides providing a dataset for research, we conduct experiments on common computational argument tasks and a novel task (rhetorical figure detection), in which we also evaluate LLMs. The experimental results highlight the challenging nature of the dataset. Our corpus is available at \url{https://github.com/VelikayaScarlet/CEDAR}.

CEDAR: A Chinese Evaluation Dataset for Computational Argumentation

Diffusion models (DMs) have recently exhibited impressive generation capability. However, their training generally requires huge computational resources and large-scale datasets. To solve these, recent studies empower DMs with Retrieval-Augmented Generation (RAG), yielding retrieval-augmented diffusion models (RDMs) that enhance performance with reduced parameters. Despite the success, RAG may introduce novel security issues that warrant further investigation. In this paper, we propose BadRDM, the first poisoning framework targeting RDMs, to systematically investigate their vulnerability to backdoor attacks. Our framework fully considers RAG's characteristics by manipulating the retrieved items for specific text triggers to ultimately control the generated outputs. Specifically, we first insert a tiny portion of images into the retrieval database as target toxicity surrogates. We then exploit the contrastive learning mechanism underlying retrieval models by designing a malicious variant that establishes robust shortcuts from triggers to toxicity surrogates. In addition, we introduce novel entropy-based selection and generative augmentation strategies for better toxicity surrogates. Extensive experiments on two mainstream tasks show that the proposed method achieves outstanding attack effects while preserving benign utility. Notably, BadRDM remains effective even under common defense strategies, further highlighting serious security concerns for RDMs.

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models

Hallucinations arise when large language models (LLMs) guess rather than acknowledge their underlying uncertainty. Existing static strategies for mitigating hallucinations have been only partially successful, largely because they do not explicitly model the information gain from interacting with the external environment. Researchers need a general method to proactively steer users toward informative clarifications, thereby unlocking the model’s effective capacity under underspecified inputs. We model the uncertainty of LLMs in interactive settings and uncover the mechanism of active calibration between model concepts and human evaluations, improving reliability. We show that calibration error in LLMs density estimation admits a non-vanishing lower bound under non-interactive learning, while interaction empirically reduces it. We further characterize that calibration error identifies informative queries and that calibration can be accelerated by shifting query distributions from imbalanced to balanced regimes. Guided by these insights, we propose a calibration-driven Interactive Learning Strategy (ILS) that selects clarification queries by optimizing calibration error, providing both theoretical guarantees and empirical gains for reliability. Code and data are available at https://github.com/zhouyeah215/Demystifying_Uncertainty.

Demystifying Uncertainty in LLMs: Active Calibration between Concepts and Human Evaluations

Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend on evolving beliefs and other agents. We present TriEx, a tri-view explainability framework that instruments sequential decision making with aligned artifacts: (i) structured first-person self-reasoning bound to an action, (ii) explicit second-person belief states about opponents updated over time, and (iii) third-person oracle audits grounded in environment-derived reference signals. This design turns explanations from free-form narratives into evidence-anchored objects that can be compared and checked across time and perspectives. Using imperfect-information strategic games as a controlled testbed, we show that TriEx enables scalable analysis of explanation faithfulness, belief dynamics, and evaluator reliability, revealing systematic mismatches between what agents say, what they believe, and what they do. Our results highlight explainability as an interaction-dependent property and motivate multi-view, evidence-grounded evaluation for LLM agents.

TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs

Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports. This covert harm is subtler than explicit misinformation, yet remains underexplored. To address this gap, we develop a multi-stage pipeline that simulates preview-based and context-based understanding, enabling construction of the MM-Misleading benchmark. Using MM-Misleading, we systematically evaluate open-source LVLMs and uncover pronounced blind spots in omission-based misleadingness detection. We further propose OMGuard, which combines (1) Interpretation-Aware Fine-Tuning for misleadingness detection and (2) Rationale-Guided Misleading Content Correction, where explicit rationales guide headline rewriting to reduce misleading impressions. Experiments show that OMGuard lifts an 8B model’s detection accuracy to the level of a 235B LVLM while delivering markedly stronger end-to-end correction. Further analysis shows that misleadingness usually arises from local narrative shifts, such as missing background, instead of global frame changes, and identifies image-driven cases where text-only correction fails, underscoring the need for visual interventions.

What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews

Large Language Model (LLM) based multi-agent systems (MAS) show strong potential for tackling complex tasks through collaborative intelligence. Monte Carlo Tree Search (MCTS) based methods provide promising approaches for enhancing MAS self-training by generating synthetic data, using Q-values to estimate agent contributions. However, relying solely on Q-values may misalign with the goal of selecting data most beneficial for MAS improvement. To address this discrepancy, we propose **D**ata **I**nfluence-oriented **T**ree **S**earch (**DITS**), a novel framework that incorporates influence scores to guide both tree search and data selection in data synthesis. By leveraging influence scores, we effectively identify the most impactful data for MAS improvement, thereby enhancing model performance. Furthermore, we derive a novel influence score estimation method tailored for non-differentiable metrics, significantly reducing computational overhead by calculating performance changes on the validation set. Extensive experiments on three different multi-agent tasks demonstrate the robustness and effectiveness of the proposed methods. Notably, our findings reveal that allocating more resources to estimate influence scores, rather than Q-values, during data synthesis can more effectively and efficiently enhance model training. The code is available at https://anonymous.4open.science/r/DITS-F1C4/.

Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search

Idiom translation remains a formidable challenge for Large Language Models (LLMs), as the constraints of static parametric memory and the noise in sentence-level retrieval often lead to literal misinterpretations. To address this, we propose DeReA, a detect-retrieve-arbitrate framework. The system employs a preference-aligned detector to identify idiomatic spans by reasoning over semantic conflicts between literal and contextual meanings. Subsequently, an idiom-centric translator invokes a fine-tuned embedding model to efficiently retrieve canonical definitions from an external knowledge base. The translator then utilizes a dual-path arbitration mechanism to select the optimal rendering by weighing the retrieval-augmented translations against direct translation. To evaluate our framework, we introduce LoMI, a high-difficulty benchmark with low data contamination. Experimental results demonstrate that DeReA significantly enhances performance across various model scales, improving GPT-5-mini by over 5.2 points in both idiomatic quality and consistency according to LLM-based metrics. Furthermore, evaluations on an emerging slang dataset from Urban Dictionary validate the potential of our approach in handling novel and evolving linguistic data. Our code is available at https://github.com/jrongqing/DeReA.

DeReA: Improving Idiom Translation with Detect-Retrieve-Arbitrate Reasoning

Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks.
However, existing LLM agents typically rely on increasingly long interaction histories, resulting in high computational cost and limited scalability.
In this paper, we propose **STEP-HRL**, a hierarchical reinforcement learning (HRL) framework that enables step-level learning by conditioning only on single-step transitions rather than full interaction histories.
STEP-HRL structures tasks hierarchically, using completed subtasks to represent *global progress* of overall task. By introducing a *local progress* module, it also iteratively and selectively summarizes interaction history within each subtask to produce a compact summary of local progress.
Together, these components yield augmented step-level transitions for both high-level and low-level policies.
Experimental results on ScienceWorld and ALFWorld benchmarks consistently demonstrate that STEP-HRL substantially outperforms baselines in terms of performance and generalization while reducing token usage. Our code is available at https://github.com/TonyStark042/STEP-HRL.

Downloads

Next from ACL 2026

RADO: Reasoning Audit-Driven Optimization for Rigorous Reasoning in High-Stakes Domains

Similar lecture

Examining Physicists' Ethical Reasoning: A Case Study