United States

The increasing integration of large language models (LLMs) into mental health applications necessitates robust frameworks for evaluating professional safety alignment. Current evaluative approaches primarily rely on refusal-based safety signals, which offer limited insight into the nuanced behaviors required in clinical practice. In mental health, clinically inadequate refusals can be perceived as unempathetic and discourage help-seeking. To address this gap, we move beyond refusal-centric metrics and introduce PsychEthicsBench, the first principle-grounded benchmark based on Australian psychology and psychiatry guidelines, designed to evaluate LLMs&#39; ethical knowledge and behavioral responses through multiple-choice and open-ended tasks with fine-grained ethicality annotations. Empirical results across 14 models reveal that refusal rates are poor indicators of ethical behavior, revealing a significant divergence between safety triggers and clinical appropriateness. Notably, we find that domain-specific fine-tuning can degrade ethical robustness, as several specialized models underperform their base backbones in ethical alignment. PsychEthicsBench provides a foundation for systematic, jurisdiction-aware evaluation of LLMs in mental health, encouraging more responsible development in this domain.

ACL 2026

PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

The increasing integration of large language models (LLMs) into mental health applications necessitates robust frameworks for evaluating professional safety alignment. Current evaluative approaches primarily rely on refusal-based safety signals, which offer limited insight into the nuanced behaviors required in clinical practice. In mental health, clinically inadequate refusals can be perceived as unempathetic and discourage help-seeking. To address this gap, we move beyond refusal-centric metrics and introduce PsychEthicsBench, the first principle-grounded benchmark based on Australian psychology and psychiatry guidelines, designed to evaluate LLMs' ethical knowledge and behavioral responses through multiple-choice and open-ended tasks with fine-grained ethicality annotations. Empirical results across 14 models reveal that refusal rates are poor indicators of ethical behavior, revealing a significant divergence between safety triggers and clinical appropriateness. Notably, we find that domain-specific fine-tuning can degrade ethical robustness, as several specialized models underperform their base backbones in ethical alignment. PsychEthicsBench provides a foundation for systematic, jurisdiction-aware evaluation of LLMs in mental health, encouraging more responsible development in this domain.

poster

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.

Multi-round Vision-Language Model (VLM) Multi-Agent Systems (MAS) offer powerful reasoning capabilities but suffer from prohibitive costs due to static panel designs, where all $N$ agents communicate at every $T$ round. This approach is fundamentally inefficient, as it ignores the \textit{context-dependent} and \textit{diminishing} marginal utility of specific agents. To address this, we propose \textbf{Nash-CredMAS}, an economic framework that transforms agent selection into a \textbf{dynamic resource allocation game}. Unlike heuristic routing or one-time pruning, our method operates in two phases: (1) \textbf{Offline Causal Value Learning}, where we employ a \textbf{doubly-robust (AIPW) estimator} to train a context-aware value function from biased interaction logs, effectively learning the true marginal contribution of agents; and (2) \textbf{Online Dynamic Auctions}, where agents bid for communication slots based on their predicted utility. We formulate the inference-time selection as a \textbf{submodular maximization problem} under budget constraints, theoretically guaranteeing a $(1 - 1/e)$-approximation of the optimal coalition via a greedy strategy. Empirically, Nash-CredMAS achieves state-of-the-art results on challenging benchmarks, including MMMU and V*-Bench, while reducing token consumption by over 25% compared to static baselines. The system naturally converges to an economic equilibrium where agents actively remain silent when their marginal value does not justify the cost.

Nash-Pruned CredMAS: Dynamic Panel Pruning for VLM-MAS using Nash-based Selection and Doubly-Robust Credits

We present a Bengali mathematical reasoning model called GanitLLM (named after the Bangla word for mathematics, "Ganit"), together with a new difficulty-aware Bengali math corpus and a curriculum-based GRPO pipeline. Bengali is one of the world's most widely spoken languages, yet existing LLMs either reason in English and then translate, or simply fail on multi-step Bengali math, in part because reinforcement learning recipes are tuned for high-resource languages and collapse under reward sparsity in low-resource settings. To address this, we construct Ganit, a rigorously filtered and decontaminated Bengali math dataset with automatic difficulty tags derived from the pass@k of a strong evaluator model. Building on this dataset, we propose Curriculum-GRPO, which combines multi-stage training (SFT + GRPO) with difficulty-aware sampling and verifiable rewards for format, numerical correctness, and Bengali reasoning. On Bn-MGSM and Bn-MSVAMP, GanitLLM-4B improves over its Qwen3-4B base by +8 and +7 accuracy points, respectively, while increasing the percentage of Bengali reasoning tokens from 14% to over 88% and reducing average solution length from 943 to 193 words.

GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO

Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are continuously released. Instead of post-training massive models for every new task or domain, we propose Supplement Generation Training (SGT), a more efficient and sustainable strategy. SGT trains a smaller LLM to generate useful supplemental text that, when appended to the original input, helps the larger LLM solve the task more effectively. These lightweight models can dynamically adapt supplements to task requirements, improving performance without modifying the underlying large models. This approach decouples task-specific optimization from large foundation models and enables more flexible, cost-effective deployment of LLM-powered agents in real-world applications.

Supplement Generation Training for Enhancing Agentic Task Performance

LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and task failures. Existing approaches operate in unstructured language spaces, generating clarifying questions through prompting strategies that lack principled criteria for determining which questions to ask and when to stop. We introduce a principled formulation of \textit{structured uncertainty} that operates directly over tool parameters and their domains, cleanly separating specification uncertainty (what the user wants) from model uncertainty (what the LLM predicts). Our formulation uses Expected Value of Perfect Information (EVPI) to quantify the disambiguation value of each potential question, balanced against aspect-based cost modeling that prevents redundant questioning. We demonstrate the versatility of this formulation through two applications. First, SAGE-Agent uses structured uncertainty for inference-time question selection, achieving 7--39% higher coverage on ambiguous tasks while reducing clarification questions by 1.5--2.7 x compared to strong prompting and uncertainty-based baselines. Second, we show that structured uncertainty provides effective training signals: uncertainty-guided reward modeling boosts When2Call accuracy from 36.5% to 65.2% (3B model) and 36.7% to 62.9% (7B model) through uncertainty-weighted GRPO training, demonstrating more sample-efficient reinforcement learning for tool-calling agents. To enable evaluation, we present \textit{ClarifyBench}, the first multi-turn dynamic tool-calling disambiguation benchmark. Our results establish structured uncertainty as a principled framework that improves both inference-time interaction efficiency and training-time sample efficiency in tool-augmented agents.

Structured Uncertainty guided Clarification for LLM Agents

The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic drift and context loss, which can lead to misleading performance metrics. In this work, we present a fully automated framework designed to address these challenges by enabling scalable, high-quality translation of datasets and benchmarks. We demonstrate that adapting test-time compute scaling strategies, specifically Universal Self-Improvement (USI) and our proposed multi-round ranking method, T-RANK, allows for significantly higher quality outputs compared to traditional pipelines. Our framework ensures that benchmarks preserve their original task structure and linguistic nuances during localization. We apply this approach to translate popular benchmarks and datasets into eight Eastern and Southern European languages (Ukrainian, Bulgarian, Slovak, Romanian, Lithuanian, Estonian, Turkish, Greek). Evaluations using both reference-based metrics and LLM-as-a-judge show that our translations surpass existing resources, resulting in more accurate downstream model assessment. We release both the framework and the improved benchmarks to facilitate robust and reproducible multilingual AI development.

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

As AI systems increasingly mediate everyday communication, large language models (LLMs) are expected not only to provide factually accurate responses but also to generate explanations that engage with users’ mental states. We build on the concept of cognitive chains—structured representations of Situation, Clue, Thought, Action, and Emotion inspired by Theory of Mind—to investigate whether conditioning LLM outputs on such belief chains improves explanation quality. Specifically, we evaluate explanations along six reader-perceived dimensions: overall quality, logical correctness, completeness, conciseness, empathy, and agreement. Prior work shows that LLM explanations often default to neutral or uncertain stances, while individuals holding strong false beliefs remain highly resistant to correction. To address this challenge, we instantiate cognitive chains from two perspectives: believers and non-believers of the news claims. Using GPT-4.1 as a role-player across these stances, we find that incorporating believers’ chains improves the perceived quality of explanations for audiences with misinformation-aligned beliefs. Our findings underscore the importance of modeling diverse mental states in explanation generation and provide the first systematic evidence that Theory-of-Mind–based cognitive chains enhance the persuasiveness of explanations in misinformation contexts.

Beyond Evidence: Belief-Chain Conditioning for Persuasive Misinformation Debunking Explanation

Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are stable in realistic settings. This work studies moral robustness in VLMs, defined as the ability to preserve moral judgments under textual and visual perturbations that do not alter the underlying moral context. We systematically probe VLMs with a diverse set of model-agnostic multimodal perturbations and find that their moral stances are highly fragile, frequently flipping under simple manipulations. Our analysis reveals systematic vulnerabilities across perturbation types, moral domains, and model scales, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion. We further show that lightweight inference-time interventions can partially restore moral stability. These results demonstrate that moral alignment alone is insufficient and that moral robustness is a necessary criterion for the responsible deployment of VLMs.

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models

Resolving anaphora requires integrating syntactic, semantic, and discourse information. Mandarin Chinese offers a particularly revealing case through the reflexive ziji, whose interpretation permits long-distance binding licensed by logophoric cues (i.e., cues relevant to discourse perspective). While these cues have been extensively studied in linguistic theory and psycholinguistic experiments, it remains an open question to what extent such cues are captured by computational models.
We investigate this question by probing large language models' sensitivity to four logophoric cues known to license long-distance binding of ziji: predicate type, perspective marking, discourse topicality, and discourse relation. Using minimal pairs and surprisal-based measures, we assess whether models exhibit systematic biases toward non-local antecedents in logophoric contexts.
Across two model families, we find that (i) models exhibit above-chance sensitivity to all four cues; (ii) lexically anchored cues are more robustly captured than discourse-level cues; and (iii) some cues generalize cross-lingually, whereas others appear to depend on language-specific training data. Taken together, these findings provide non-English evidence that large language models capture certain aspects of logophoricity, yet continue to struggle with discourse-level representations that are central to human anaphora resolution. Code and data are available at: https://github.com/yunfang-dong/mandarin-logophoricity-llm

 Do Language Models Use Logophoric Cues? Evidence from Mandarin Chinese Long-Distance Reflexive

Masked Diffusion Language Models (DLMs) have recently emerged as a promising alternative to traditional Autoregressive Models (ARMs). DLMs employ transformer encoders with bidirectional attention, enabling parallel token generation while maintaining competitive performance. Although their efficiency and effectiveness have been extensively studied, the internal mechanisms that govern DLMs remain largely unexplored. In this work, we conduct an empirical analysis of DLM attention patterns, focusing on the attention sinking phenomenon, an effect previously observed in various transformer-based architectures. Our findings reveal that DLMs also exhibit attention sinks, but with distinct characteristics. First, unlike in ARMs, the sink positions in DLMs tend to shift throughout the generation process, displaying a dynamic behaviour. Second, while ARMs are highly sensitive to the removal of attention sinks, DLMs remain robust: masking sinks leads to only a minor degradation in performance. These results provide new insights into the inner workings of diffusion-based language models and highlight fundamental differences in how they allocate and utilize attention compared to autoregressive models.

Attention Sinks in Diffusion Language Models

When LLM agents work together, they seem to be more powerful than a single LLM in mathematical question answering. However, are they also more robust to adversarial inputs? We investigate this question using adversarially perturbed math questions. These perturbations include punctuation noise with three intensities (10%, 30%, 50%), plus real-world and human-like typos (WikiTypo, R2ATA). Using a unified sampling-and-voting framework (Agent Forest), we evaluate six open-source models (Qwen3-4B/14B, Llama3.1-8B, Mistral-7B, Gemma3-4B/12B) across four benchmarks (GSM8K, MATH, MMLU–Math, MultiArith), with various numbers of agents n = {1,2,5,10,15,20,25}. Our findings show that 1) Noise type matters: punctuation noise harm scales with its severity, and the human typos remain the dominant bottleneck, yielding the largest gaps to Clean accuracy and the highest attack success rate (ASR) even with a large number of agents; 2) Collaboration reliably improves accuracy as the number of agents, n, increases, with the largest gains from n=1 to n=5 and diminishing returns beyond n$\approx$10. However, the adversarial robustness gap persists regardless of the agent count.

Downloads

Next from ACL 2026

Nash-Pruned CredMAS: Dynamic Panel Pruning for VLM-MAS using Nash-based Selection and Doubly-Robust Credits

Similar lecture

Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES