Morocco

This paper examines how Large Language Models (LLMs) reproduce societal norms, particularly heterocisnormativity, and how these norms translate into measurable biases in their text generations. We investigate whether explicit information about a subject&#39;s gender or sexuality influences LLM responses across three subject categories: queer-marked, non-queer-marked, and the normalized &quot;unmarked&quot; category. Representational imbalances are operationalized as measurable differences in English sentence completions across four dimensions: sentiment, regard, toxicity, and prediction diversity. Our findings show that Masked Language Models (MLMs) produce the least favorable sentiment, higher toxicity, and more negative regard for queer-marked subjects. Autoregressive Language Models (ARLMs) partially mitigate these patterns, while closed-access ARLMs tend to produce more harmful outputs for unmarked subjects. Results suggest that LLMs reproduce normative social assumptions, though the form and degree of bias depend strongly on specific model characteristics, which may redistributeвЂ”but not eliminateвЂ”representational harms.

EACL 2026

QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Task

bias in llms

lgbtqia+

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

This paper examines how Large Language Models (LLMs) reproduce societal norms, particularly heterocisnormativity, and how these norms translate into measurable biases in their text generations. We investigate whether explicit information about a subject's gender or sexuality influences LLM responses across three subject categories: queer-marked, non-queer-marked, and the normalized "unmarked" category. Representational imbalances are operationalized as measurable differences in English sentence completions across four dimensions: sentiment, regard, toxicity, and prediction diversity. Our findings show that Masked Language Models (MLMs) produce the least favorable sentiment, higher toxicity, and more negative regard for queer-marked subjects. Autoregressive Language Models (ARLMs) partially mitigate these patterns, while closed-access ARLMs tend to produce more harmful outputs for unmarked subjects. Results suggest that LLMs reproduce normative social assumptions, though the form and degree of bias depend strongly on specific model characteristics, which may redistributeвЂ”but not eliminateвЂ”representational harms.

poster

#### *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)*<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://underline.io/events/522/reception','_blank')">Go to Workshops and Tutorials Program</button></html>
<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 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. 

Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms such as differential privacy (DP) reduce this leakage, but incur large drops in utility. Based on a comprehensive study using circuit discovery to identify the computational circuits responsible PII leakage in LMs, we hypothesize that specific PII leakage circuits in LMs should be responsible for this behavior. Therefore, we propose PATCH: Privacy-Aware Targeted Circuit Patching, a novel approach that first identifies and subsequently directly edits PII circuits to reduce leakage. PATCH achieves better privacy-utility trade-off than existing defenses, e.g., reducing recall of PII leakage from LMs by up to 65%. Finally, PATCH can be combined with DP to reduce recall of residual leakage of an LM to as low as 0.01%. Our analysis shows that PII leakage circuits persist even after the application of existing defense mechanisms. In contrast, PATCH can effectively mitigate their impact.

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing

Information Extraction (IE), encompassing Named Entity Recognition (NER), Named Entity Linking (NEL), and Relation Extraction (RE), is critical for transforming the rapidly growing volume of scientific publications into structured, actionable knowledge. This need is especially evident in fast-evolving biomedical fields such as the gut-brain axis, where research investigates complex interactions between the gut microbiota and brain-related disorders. Existing biomedical IE benchmarks, however, are often narrow in scope and rely heavily on distantly supervised or automatically generated annotations, limiting their utility for advancing robust IE methods. We introduce GutBrainIE, a benchmark based on more than 1,600 PubMed abstracts, manually annotated by biomedical and terminological experts with fine-grained entities, concept-level links, and relations. While grounded in the gut-brain axis, the benchmark's rich schema, multiple tasks, and combination of highly curated and weakly supervised data make it broadly applicable to the development and evaluation of biomedical IE systems across domains.

A Domain-Specific Curated Benchmark for Entity and Document-Level Relation Extraction

he rapid integration of large language models (LLMs) into high-stakes legal work has exposed a critical gap: no benchmark exists to systematically stress-test their reliability against the nuanced, adversarial, and often subtle flaws present in real-world contracts. To address this, we introduce CLAUSE, a first-of-its-kind benchmark designed to evaluate the fragility of an LLM's legal reasoning. We study the capabilities of LLMs to detect and reason about fine-grained discrepancies by producing over 7500 real-world perturbed contracts from foundational datasets like CUAD and ContractNLI. Our novel, persona-driven pipeline generates 10 distinct anomaly categories, which are then validated against official statutes using a Retrieval-Augmented Generation (RAG) system to ensure legal fidelity. We use CLAUSE to evaluate leading LLMs’ ability to detect embedded legal flaws and explain their significance. Our analysis shows a key weakness: these models often miss subtle errors and struggle even more to justify them legally. Our work outlines a path to identify and correct such reasoning failures in legal AI.

Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities

We introduce ChemComp, the first chemistry-focused benchmark for evaluating compositional multi-hop reasoning in large language models (LLMs). Our automated pipeline constructs benchmarks from proprietary or public data by integrating generative reasoning models, chemical named-entity recognition, and external knowledge bases to build knowledge graphs. Applied to recent chemistry literature, this approach minimizes overlap with LLM pretraining data. The resulting dataset comprises 1,188 multi-hop questions, refined through domain-expert feedback and robust evaluation protocols. Using ChemComp, we systematically compare LLM performance with and without retrieval augmentation, including an idealized gold-context scenario. Our results show that even state-of-the-art models struggle with compositional reasoning: retrieval significantly improves accuracy, yet reasoning errors persist even under perfect retrieval. These findings highlight the limitations of current LLMs and the critical role of retrieval-augmented methods in scientific reasoning. Furthermore, our pipeline is generalizable with fine-tuning, enabling the creation of challenging multi-hop reasoning benchmarks across domains and proprietary datasets.

Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Benchmark

We introduce SymPyBench, a large-scale synthetic benchmark of 15K university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectively infinite range of input configurations, and is accompanied by structured, step-by-step reasoning and executable Python code that produces the ground-truth solution for any parameter set. The benchmark contains three question types: MC-Symbolic (multiple-choice with symbolic options), MC-Numerical (multiple-choice with numerical options), and free-form (open-ended responses). These diverse formats test complementary reasoning skills. In addition to standard accuracy, we introduce three new metrics: Consistency Score, Failure Rate, and Confusion Rate, that quantify variability and uncertainty across problem variants. Experiments with state-of-the-art instruction-tuned language models reveal both strengths and limitations in scientific reasoning, positioning SymPyBench as a foundation for developing more robust and interpretable reasoning systems.

SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code

When language models correctly parse "The cat that the dog chased meowed,'' are they analyzing syntax or simply familiar with dogs chasing cats? Despite extensive benchmarking, we lack methods to distinguish structural understanding from semantic pattern matching. We introduce **CenterBench**, a dataset of 9,720 comprehension questions on center-embedded sentences (like "The cat [that the dog chased] meowed'') where relative clauses nest recursively, creating processing demands from simple to deeply nested structures. Each sentence has a syntactically identical but semantically implausible counterpart (e.g., mailmen prescribe medicine, doctors deliver mail) and six comprehension questions testing surface understanding, syntactic dependencies, and causal reasoning. Testing six models reveals that performance gaps between plausible and implausible sentences widen systematically with complexity, with models showing median gaps up to 26.8 percentage points, quantifying when they abandon structural analysis for semantic associations. Notably, semantic plausibility harms performance on questions about resulting actions, where following causal relationships matters more than semantic coherence. Reasoning models improve accuracy while their traces expose semantic shortcuts, overthinking, and answer refusal. Unlike models whose plausibility advantage systematically widens with complexity, humans show variable semantic effects. CenterBench provides the first framework to identify when models shift from structural analysis to pattern matching.

The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts

Extremist groups develop complex in-group language, also referred to as cryptolects, to exclude or mislead outsiders. We investigate the ability of current language technologies to detect and interpret the cryptolects of two online extremist platforms. Evaluating eight models across six tasks, our results indicate that general purpose LLMs cannot consistently detect or decode extremist language. However, performance can be significantly improved by domain adaptation and specialised prompting techniques. These results provide important insights to inform the development and deployment of automated moderation technologies. We further develop and release novel labelled and unlabelled datasets, including 19.4M posts from extremist platforms and lexicons validated by human experts.

IYKYK: Using language models to decode extremist cryptolects

We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean queries are the primary mechanism for literature retrieval in this domain and must achieve high recall while maintaining reasonable precision---a challenging balance that existing prompt-based LLM approaches often struggle to achieve. A major limitation in this space is the lack of ground-truth best Boolean queries for each topic, which makes supervised fine-tuning impractical. AutoBool addresses this challenge by leveraging RL to directly optimize query generation against retrieval performance metrics, without requiring ideal target queries. To support this effort, we create and release the largest dataset of its kind: 65 588 topics in total for training and evaluating the task of automatic Boolean query formulation. Experiments on our new dataset and two established datasets (CLEF TAR and Seed Collection) show that AutoBool significantly outperforms zero-shot/few-shot prompting and matches or exceeds the effectiveness of much larger GPT-based models (e.g., GPT-4o, O3) using smaller backbones. It also approaches effectiveness of expert-authored queries while retrieving 10вЂ“16 times fewer documents. Ablation studies reveal the critical roles of model backbone, size, decoding temperature, and prompt design. Code and data are available at https://anonymous.4open.science/r/AutoBool-B3E5/.

AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation

Understanding narratives requires identifying which events are most salient for a story's progression. We present a contrastive learning framework for modeling narrative salience that learns story embeddings from narrative twins: stories that share the same plot but differ in surface form. Our model is trained to distinguish a story from both its narrative twin and a distractor with similar surface features but different plot. Using the resulting embeddings, we evaluate four narratologically motivated operations for inferring salience (deletion, shifting, disruption, and summarization). Experiments on short narratives (ROCStories) and longer Wikipedia plot summaries show that contrastively learned story embeddings outperform a masked-language-model baseline, and that summarization is the most reliable operation for identifying salient sentences. If retellings are not available, random dropout can be used to generate narrative twins from a single story. Effective distractors can be obtained either by prompting LLMs or, in long-form narratives, by using different parts of the same story.

Contrastive Learning with Narrative Twins for Modeling Story Salience

The intentional creation and spread of disinformation poses a significant threat to public discourse. However, existing English datasets and research rarely address the intentionality behind the disinformation. This work presents MALINT, the first human-annotated English corpus developed in collaboration with expert fact-checkers to capture disinformation and its malicious intent. We utilize our novel corpus to benchmark 12 language models, including small language models (SLMs) such as BERT and large language models (LLMs) like Llama 3.3, on binary and multilabel intent classification tasks. Moreover, inspired by inoculation theory from psychology and communication studies, we investigate whether incorporating knowledge of malicious intent can improve disinformation detection. To this end, we propose intent-based inoculation, an intentвЂ‘augmented reasoning for LLMs that integrates intent analysis to mitigate the persuasive impact of disinformation. Analysis on six disinformation datasets, five LLMs, and seven languages shows that intentвЂ‘augmented reasoning improves zeroвЂ‘shot disinformation detection. To support research in intentвЂ‘aware disinformation detection, we release the MALINT dataset with annotations from each annotation step.

Downloads

Next from EACL 2026

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing

Similar lecture

How to Make Virtual Conferences Queer-Friendly: A Guide

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES