Morocco

Large language models (LMs) excel across diverse domains, yet require substantial computational resources during inference. Model compression has proved a successful direction towards reducing these costs, exemplified by the performance preservation on general-purpose benchmarks. However, model compression methods can substantially degrade performance for specialized domains, such as law and healthcare. We therefore present JointCal, a novel approach that simultaneously models the importance of weights to both specialized and general capabilities. This leverages a unique layer-wise reconstruction loss formulation that captures the activations from different domains and the interactions between them. Using a battery of experiments across tasks and models, we empirically show that JointCal offers consistent improvements on specialized benchmarks, while preserving overall performance. In contrast to prior work towards domain-adapted compression, our approach does not require any resource-intensive model training procedures, reducing the duration of compression from hours to minutes.

EACL 2026 Main Conference

Compressing Language Models for Specialized Domains

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. 

Retrieval-Augmented Generation (RAG) systems degrade sharply under extreme noise,where irrelevant or redundant passages dominate. Current methods-fixed top-k retrieval, cross-encoder reranking, or policy based iteration-depend on static heuristics or costly reinforcement learning, failing to assess evidence sufficiency, detect subtle mismatches, or reduce redundancy, leading to hallucinations and poor grounding. We introduce ReflectiveRAG, a lightweight yet reasoning-driven architecture that enhances factual grounding through two complementary mechanisms: Self-Reflective Retrieval (SRR) and Contrastive Noise Removal (NR). SRR employs small language model as a decision controller that iteratively evaluates evidence sufficiency, enabling adaptive query reformulation without fixed schedules or policy training. NR further refines retrieved content via embedding-based contrastive filtering, enforcing semantic sparsity and removing redundant or tangential passages. Evaluated on WebQuestions, HotpotQA (distractor setting) and InternalQA with 50M Common Crawl distractors, ReflectiveRAG achieves substantial gains over strong baselines-including DeepRAG-improving EM by +2.7 pp and F1 by +2.5 pp, while reducing evidence redundancy by 30.88% with only 18 ms additional latency. Ablation studies confirm that SRR and NR jointly drive both factual accuracy and efficiency, validating our central claim that retrieval reasoning and contrastive filtering can outperform large-scale policy optimization in RAG.

ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented Generation

Public opinion surveys show cross-cultural differences in political opinions between socio-cultural contexts. However, there is no clear evidence whether these differences translate to cross-lingual differences in multilingual large language models (MLLMs). We analyze whether opinions transfer between languages or whether there are separate opinions for each language in MLLMs of various sizes across five Western languages. We evaluate MLLMs' opinions by prompting them to report their (dis)agreement with political statements from voting advice applications. To better understand the interaction between languages in the models, we evaluate them both before and after aligning them with more left or right views using direct preference optimization and English alignment data only. Our findings reveal that unaligned models show only very few significant cross-lingual differences in the political opinions they reflect. The political alignment shifts opinions almost uniformly across all five languages. We conclude that in Western language contexts, political opinions transfer between languages, demonstrating the challenges in achieving explicit socio-linguistic, cultural, and political alignment of MLLMs.

Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs

We present AraBabyTalk-EGY, an enriched release of the Egyptian Arabic CHILDES corpus, that opens the child-adult interactions genre to modern Arabic NLP research. Starting from the original CHILDES recordings and IPA transcriptions of caregiver-child sessions, we (i) map each IPA token to fully diacritized Arabic script, and (ii) add core part-of-speech tags and lemmas aligned with existing dialectal Arabic morphological resources. These layers yield ~26K annotated tokens suitable for both text- and speech-based NLP tasks. We provide a benchmark on morphological disambiguation and Arabic ASR. We outline lexical and morphosyntactic differences between AraBabyTalk-EGY and general Egyptian Arabic resources, highlighting the value of genre-specific training data for language acquisition studies and Arabic speech technology.

Computational Benchmarks for Egyptian Arabic Child Directed Speech

Reliable uncertainty quantification (UQ) is essential when employing large language models (LLMs) in high-risk domains such as clinical question answering (QA). In this work, we evaluate uncertainty estimation methods for clinical QA focusing, for the first time, on eleven clinical specialties and six question types, and across ten open-source LLMs (general-purpose, biomedical, and reasoning models). We analyze score-based UQ methods, present a case study introducing a novel lightweight method based on behavioral features derived from reasoning-oriented models, and examine conformal prediction as a complementary set-based approach. Our findings reveal that uncertainty reliability is not a monolithic property, but one that depends on clinical specialty and question type due to shifts in calibration and discrimination. Our results highlight the need to select or ensemble models based on their distinct, complementary strengths and clinical use.

Mind the Gap: Benchmarking LLM Uncertainty and Calibration with Specialty-Aware Clinical QA and Reasoning-Based Behavioural Features

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their stability, interpretability, and show their practical utility. Over 50% of the features remain consistent across random seeds, and reconstruction quality is preserved. SAE features capture general acoustic and semantic information as well as specific events, including environmental noises and paralinguistic sounds (e.g. laughter, whispering) and disentangle them effectively, requiring removal of only 19-27% of features to erase a concept. Feature steering reduces Whisper’s false speech detections by 70% with negligible WER increase, demonstrating real-world applicability. Finally, we find SAE features correlated with human EEG activity during speech perception, indicating alignment with human neural processing. The code and checkpoints are available at https://github.com/audiosae/audiosae_demo.

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Persona-assigned large language models (LLMs) are used in domains such as education, healthcare, and sociodemographic simulation. Yet, they are typically evaluated only in short, single-round settings that do not reflect real-world usage. We introduce an evaluation protocol that combines long persona dialogues (over 100 rounds) and evaluation datasets to create dialogue-conditioned benchmarks that can robustly measure long-context effects. We then investigate the effects of dialogue length on persona fidelity, instruction-following, and safety of seven state-of-the-art open- and closed-weight LLMs. We find that persona fidelity degrades over the course of dialogues, especially in goal-oriented conversations, where models must sustain both persona fidelity and instruction following. We identify a trade-off between fidelity and instruction following, with non-persona baselines initially outperforming persona-assigned models; as dialogues progress and fidelity fades, persona responses become increasingly similar to baseline responses. Our findings highlight the fragility of persona applications in extended interactions and our work provides a protocol to systematically measure such failures.

Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions

Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabeled data using limited labeled data from known categories. Due to the lack of supervision, previous GCD methods face significant challenges, such as difficulty in rectifying errors for confusing instances, and inability to effectively uncover and leverage the semantic meanings of discovered clusters. Therefore, additional annotations are usually required for real-world applicability. However, human annotation is extremely costly and inefficient. To address these issues, we propose DeLFGCD , a unified framework for generalized category discovery that actively learns from diverse and collaborative LLM feedback. Our approach leverages three different types of LLM feedback to: (1) improve instance-level contrastive features, (2) generate category descriptions, and (3) align uncertain instances with LLM-selected category descriptions. Extensive experiments demonstrate the superior performance of DeLFGCD over state-of-the-art models across diverse datasets, metrics, and supervision settings. Our code is available at https://anonymous.4open.science/r/GCD-LLM-0DB9

Active Generalized Category Discovery with Diverse LLM Feedback

Large language models (LLMs) are increasingly evaluated on reasoning tasks, yet their logical abilities remain contested. To address this, we study LLMs' reasoning in a well-defined fragment of logic: syllogistic reasoning. We cast the problem as premise selection and construct controlled datasets to isolate logical competence. Beyond evaluation, an open challenge is enabling LLMs to acquire abstract inference patterns that generalize to novel structures. We propose to apply few-shot meta-learning to this domain, thereby encouraging models to extract rules across tasks rather than memorize patterns within tasks. Although meta-learning has been little explored in the context of logic learnability, our experiments show that it is effective: small models (1.5B-7B) fine-tuned with meta-learning demonstrate strong gains in generalization, with especially pronounced benefits in low-data regimes. These meta-learned models outperform GPT-4o and o3-mini on our syllogistic reasoning task.

Teaching Small Language Models to Learn Logic through Meta-Learning

We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (internals). Using this framework, we examine over 20 OLMo, Llama, and Mistral models, bridging behavioral and internal perspectives for toxicity for the first time. Our results show that LMs strongly encode information about the toxicity level of inputs and subsequent outputs, particularly in lower layers. Focusing on how unique LMs differ offers both correlative and causal evidence that they generate less toxic output when strongly encoding information about the input toxicity. We also highlight the heterogeneity of toxicity, as model behavior and internals vary across unique attributes such as Threat. Finally, four case studies analyzing detoxification, multi-prompt evaluations, model quantization, and pre-training dynamics underline the practical impact of aligned probing with further concrete insights. Our findings contribute to a more holistic understanding of LMs, both within and beyond the context of toxicity.

Aligned Probing: Relating Toxic Behavior and Model Internals

Large Language Models (LLMs) have great potential to accelerate and support scholarly peer review and are increasingly used as fully automatic review generators (ARGs). However, potential biases and systematic errors may pose significant risks to scientific integrity; understanding the specific capabilities and limitations of state-of-the-art ARGs is essential. We focus on a core reviewing skill that underpins high-quality peer review: detecting faulty research logic. This involves evaluating the internal consistency between a paper’s results, interpretations, and claims. We present a fully automated counterfactual evaluation framework that isolates and tests this skill under controlled conditions. Testing a range of ARG approaches, we find that, contrary to expectation, flaws in research logic have no significant effect on their output reviews. Based on our findings, we derive three actionable recommendations for future work and release our counterfactual dataset and evaluation framework publicly.

Downloads

Next from EACL 2026 Main Conference

ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES