Morocco

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have demonstrated remarkable performance in a wide range of tasks. However, they still lack human cognition to balance factuality and safety. Bearing the resemblance, we argue that both factual and safety failures in LLMs arise from a &quot;concept misalignment&#39;&#39; in their internal representations rather than addressing those as entirely separate alignment issues. We hypothesize that an external network, trained to understand the fluctuations, can selectively intervene in the model to regulate falsehood into truthfulness and unsafe output into safe output without fine-tuning the model parameters themselves. Reflecting the hypothesis, we propose ARREST (Adversarial Resilient Regulation Enhancing Safety and Truth), a unified framework that identifies and corrects drifted features, engaging both soft and hard refusals in addition to factual corrections. Our empirical results show that ARREST not only regulates misalignment but is also more versatile compared to the RLHF-aligned modelsin generating soft refusals due to adversarial training. We make our codebase available at https://anonymous.4open.science/r/ARREST-LLM .

EACL 2026

ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models

safety alignment

large language model

hallucination

mitigation

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have demonstrated remarkable performance in a wide range of tasks. However, they still lack human cognition to balance factuality and safety. Bearing the resemblance, we argue that both factual and safety failures in LLMs arise from a "concept misalignment'' in their internal representations rather than addressing those as entirely separate alignment issues. We hypothesize that an external network, trained to understand the fluctuations, can selectively intervene in the model to regulate falsehood into truthfulness and unsafe output into safe output without fine-tuning the model parameters themselves. Reflecting the hypothesis, we propose ARREST (Adversarial Resilient Regulation Enhancing Safety and Truth), a unified framework that identifies and corrects drifted features, engaging both soft and hard refusals in addition to factual corrections. Our empirical results show that ARREST not only regulates misalignment but is also more versatile compared to the RLHF-aligned modelsin generating soft refusals due to adversarial training. We make our codebase available at https://anonymous.4open.science/r/ARREST-LLM .

technical paper

#### *Message from the General Chair, Aline Villavicencio*
I’m delighted and honoured to welcome you to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026), taking place in the beautiful city of Rabat, in Morocco, in March 24-29, 2026. EACL is the flagship European conference of the Association and EACL 2026 proudly continues our field’s tradition of excellence in scholarship, innovation, and inclusivity. I am deeply grateful to the many volunteers whose dedication, generosity, and tireless efforts have made this conference possible.
For the first time EACL is being hosted in the African continent. This is an important milestone for our community, and we are grateful to our Moroccan hosts for enabling this historic moment by bringing this edition of EACL to Rabat. We are also delighted that the Second Arabic NLP School is co-located with EACL. We hope attendees enjoy this wonderful opportunity to strengthen ties with the Computational Linguistics communities across the African continent. *[Read full message](https://drive.google.com/file/d/14NlmHvwM6fPJuMmOvVh7K0vtQbEyv3SZ/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://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</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 EACL 2026". 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 are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.eacl.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/eacl2026

Registration Required

Welcome to the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL). EACL 2026 will be held in Rabat, Morocco, from March 24–29, 2026. 

Administrative phone tasks drain roughly 1 trillion annually from U.S. healthcare, with over 500 million insurance–benefit verification calls manually handled in 2024. We introduce INSURE-Dial, to our knowledge the first public benchmark for developing and assessing compliance-aware voice agents for phase-aware call auditing with span-based compliance verification. The corpus includes 50 de-identified, AI-initiated calls with live insurance representatives (mean 71 turns/call) and 1,000 synthetically generated calls that mirror the same workflow. All calls are annotated with a phase-structured JSON schema covering IVR navigation, patient identification, coverage status, medication checks (up to two drugs), and agent identification (CRN), and each phase is labeled for Information and Procedural compliance under explicit ask/answer logic. We define two novel evaluation tasks: (1) Phase Boundary Detection (span segmentation under phase-specific acceptance rules) and (2) Compliance Verification (IC/PC decisions given fixed spans). Per-phase scores are strong across small, low-latency baselines, but end-to-end reliability is constrained by span-boundary errors. On real calls, full-call exact segmentation is low, showing a gap between conversational fluency and audit-grade evidence.

INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection

Large language models (LLMs) have shown promising accuracy in predicting survey responses and policy preferences, which has increased interest in their potential to represent human interests in various domains. Most existing research has focused on "behavioral cloning", effectively evaluating how well models reproduce individuals' expressed preferences. Drawing on theories of political representation, we highlight an underexplored design trade-off: whether AI systems should act as "delegates", mirroring expressed preferences, or as "trustees", exercising judgment about what best serves an individual's interests. This trade-off is closely related to issues of LLM sycophancy, where models can encourage behavior or validate beliefs that may be aligned with a user's short-term preferences, but is detrimental to their long-term interests. Through a series of experiments simulating votes on various policy issues in the U.S. context, we apply a temporal utility framework that weighs short and long-term interests (simulating a trustee role) and compare voting outcomes to behavior-cloning models (simulating a delegate). We find that trustee-style predictions weighted toward long-term interests produce policy decisions that align more closely with expert consensus on well-understood issues, but also show greater bias toward models' default stances on topics lacking clear agreement. These findings reveal a fundamental trade-off in designing AI systems to represent human interests. Delegate models better preserve user autonomy but may diverge from well-supported policy positions, while trustee models can promote welfare on well-understood issues yet risk paternalism and bias on subjective topics.

From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLMs

Ancient people translated classical Chinese into Japanese by annotating around each character. We abstract this process as sequence tagging tasks and fit them into modern language technologies. The research of this annotation and translation system is a facing low-resource problem. We release this problem by introducing a LLM-based annotation pipeline and construct a new dataset from digitalized open-source translation data. We show that under the low-resource setting, introducing auxiliary Chinese NLP tasks has a promoting effect on the training of sequence tagging tasks. We also evaluate the performance of large language models. They achieve high scores in direct machine translation, but they are confused when being asked to annotate characters. Our method could work as the reinforcement of LLMs.

Translation via Annotation: A Computational Study of Translating Classical Chinese into Japanese

Commonsense reasoning (CSR) is a popular set of tasks used to evaluate large language model performance. However, what constitutes common sense might not apply to disabled people, leaving them out of AI progress by ignoring their identities. This paper investigates how datasets and models deal with disability in commonsense reasoning through a case study of three types of disabilities: autism, vision impairments, and long COVID. We first obtain annotations from disabled and non-disabled persons on n = 300 samples of three widely used CSR datasets (CommonsenseQA, Social IQA, Physical IQA) for ableism, which we define as entries in which gold labels assume a lack of disability, finding that 15% of entries contain ableism. Then, we investigate LLMs' ability to flag ableism in CSR instances, and their flexibility to adapt to disability contexts---whether the CSR gold answer changes if the person is disabled. Our results show that the three LLMs tested have low sensitivity to human-detected ableism occurrences but still detect 5 to 25% of entries as ableist. Our findings call into question whether relying on such assumption-laden commonsense reasoning benchmarks risks leaving disabled people behind in the AI world.

Common Sense or Ableism? Rethinking Commonsense Reasoning Through the Lens of Disability

Large Language Models exhibit implicit personalities in their generation, but reliably controlling or aligning these traits to meet specific needs remains an open challenge. The need for effective mechanisms for behavioural manipulation of the model during generation is a critical gap in the literature that needs to be fulfilled. Personality-aware LLMs hold a promising direction towards this objective. However, the relationship between these psychological constructs and their representations within LLMs remains underexplored and requires further investigation. Moreover, it is intriguing to understand and study the use of these representations to steer the models' behaviour. We propose a novel pipeline that extracts hidden state activations from transformer layers using the Big Five Personality Traits (Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism), which is a comprehensive and empirically validated framework to model human personality applies low-rank subspace discovery methods, and identifies trait-specific optimal layers across different model architectures for robust injection. The resulting personality-aligned directions are then operationalised through a flexible steering framework with dynamic layer selection, enabling precise control of trait expression in LLM outputs. Our findings reveal that personality traits occupy a low-rank shared subspace, and that these latent structures can be transformed into actionable mechanisms for effective steering through careful perturbations without impacting the fluency, variance and general capabilities, helping to bridge the gap between psychological theory and practical model alignment

Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs

We find that correct-to-incorrect sycophancy signals are most linearly accessible within multi-head attention activations. Motivated by the linear representation hypothesis, we train linear probes across the residual stream, multilayer perceptron (MLP), and attention layers to analyze where these signals emerge. Although separability appears in the residual stream and MLPs, steering using these probes is most effective in a sparse subset of middle-layer attention heads. Using TruthfulQA as the base dataset, we find that probes trained on it transfer effectively to other factual QA benchmarks. Furthermore, comparing our discovered direction to previously identified “truthful” directions reveals limited overlap, suggesting that factual accuracy, and deference resistance, arise from related but distinct mechanisms. Attention-pattern analysis further indicates that the influential heads attend disproportionately to expressions of user doubt, contributing to sycophantic shifts. Overall, these findings suggest that sycophancy can be mitigated through simple, targeted linear interventions that exploit the internal geometry of attention activations. Code will be released upon publication.

Sycophancy Hides Linearly in the Attention Heads

Entity structure extraction, which aims to extract entities and their associated attributeвЂ“value structures from text, is an essential task for text understanding and knowledge graph construction. Existing methods based on large language models (LLMs) typically rely heavily on predefined entity attribute schemas or annotated datasets, often leading to incomplete extraction results. To address these challenges, we introduce ZOES, a novel approach to entity structure extraction that does not require any schema or annotated samples. ZOES operates via a principled mechanism of enrichment, refinement, and unification, based on the insight that an entity and its associated structure are mutually reinforcing. Experiments demonstrate that ZOES consistently enhances LLMs' ability to extract more complete entity structures across three different domains, showcasing both the effectiveness and generalizability of the method. These findings suggest that such an enrichment, refinement, and unification mechanism may serve as a principled approach to improving the quality of LLM-based entity structure discovery in various scenarios.

Zero-Shot Open-Schema Entity Structure Discovery

Dynamic web navigation is challenging due to infinite decision space and the constantly changing nature of cyberspace. Existing methods rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models. In this paper, we propose HintNavigator, a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration (ICE). Inspired by human cognitive planning process, we categorize the interaction history into Declarative History (environment observations) and Procedural History (action trajectories) to enhance historical reflection capability. These dual-history streams are dynamically integrated through specialized cognitive agents, enabling effective self-directed backtracking guided by working memory consolidation. Experiments show that HintNavigator achieves state-of-the-art performance among open-source LLM agents, surpassing proprietary model Claude-3.5 Sonnet on the WebArena benchmark.

Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration

Knowledge editing (KE) has recently emerged as a promising technique to update specific facts in large language models (LLMs) without full retraining. While existing KE methods show promising results on general-domain benchmarks, their effectiveness in the medical domain remains largely unexplored. Medical knowledge editing poses unique challenges, requiring models not only to memorize new facts but also to internalize and generalize them for reliable and interpretable clinical decision-making. In this work, we propose MedEditBench, a rigorous evaluation framework for assessing medical knowledge editing. Our preliminary results reveal that current KE paradigm, which directly edits simple answers to the LLMs, often leads to superficial updates with poor generalization. To address this, we introduce Self-Generated Rationale Editing (SGR-Edit), which leverages model-generated rationales as editing targets, enabling deeper knowledge integration. Extensive experiments across diverse LLMs and KE methods demonstrate that SGR-Edit consistently improves editing efficacy and generalization. Furthermore, we examine the impact of sequential edits on in-domain medical knowledge, external-domain knowledge, as well as general model capabilities, offering practical insights for deploying KE in real-world medical applications.

Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing

Figurative language, particularly fixed figurative expressions (FFEs) such as idioms and proverbs, poses persistent challenges for large language models (LLMs). Unlike literal phrases, FFEs are culturally grounded, largely non-compositional, and conventionally fixed, making them especially vulnerable to figurative hallucination. We define figurative hallucination as the generation or endorsement of expressions that sound idiomatic and plausible but do not exist as authentic figurative expressions in the target language. We introduce FFEHallu, the first comprehensive benchmark for evaluating figurative hallucination in LLMs, with a focus on Persian, a linguistically rich yet underrepresented language. FFEHallu consists of 600 carefully curated instances spanning three complementary tasks: (i) FFE generation from meaning, (ii) detection of fabricated FFEs across four controlled construction categories, and (iii) FFE to FFE translation from English to Persian. Evaluating six state of the art multilingual LLMs, we find systematic weaknesses in figurative competence and cultural grounding. While models such as GPT4.1 demonstrate relatively strong performance in rejecting fabricated FFEs and retrieving authentic ones, most models struggle to reliably distinguish real expressions from high quality fabrications and frequently hallucinate during cross lingual translation. These findings reveal substantial gaps in current LLMs handling of figurative language and underscore the need for targeted benchmarks to assess and mitigate figurative hallucination.

Downloads

Next from EACL 2026

INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection

Similar lecture

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EACL 2026

INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection

Similar lecture

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads