Morocco

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at the cost of numerous expensive calls and a much greater amount of data. We propose a novel blueprint for efficient fine-tuning that uses reasoning only for complex data identified by entropy. Specifically, across three small open models (3B) we split the training data into complexity categories by a single token answer entropy (ROC AUC 0.73), fine-tune large language models (LLMs) via SFT and distillation, and show that our pipeline significantly outperforms the standard SFT approach (0.58 vs 0.45 average accuracy) and outperforms the distillation approach (0.58 vs 0.56 average accuracy) while using 81% less data. We publish our code and data to facilitate further research in this direction.

EACL 2026

Complexity-aware fine-tuning

uncertainty estimation

distillation

efficient fine-tuning

### Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

Welcome to the 2025 meeting of the Nations of the Americas Chapter of the Association for Computational Linguistics! I am proud to help organize the first NAACL conference to carry the new name of our organization, one that emphasizes inclusion for all of the Americas. I am also pleased to welcome you to Albuquerque, New Mexico, a state whose unique blend of cultural influences will make for an excellent backdrop for NAACL 2025, especially with this year’s special theme on NLP in a Multicultural World. 
**[Continue reading...](https://drive.google.com/file/d/1jX-qGhqVSZZCIrAnJaz798pflu5Irrdn/view?usp=sharing)**

*- Colin Cherry, Google, NAACL 2025 General Chair* 

[![](https://assets.underline.io/markdown_image/1/image/b087f8a4dc5816d6e1a6514e59c59ac3.png)](https://drive.google.com/file/d/1T96GzPqObXrMln2BMByCSXTSizjTg69P/view?usp=sharing)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

To access NAACL 2025 event page you are required to register. Please follow [**this link**](https://2025.naacl.org/registration/registration/) to register. Access will depend on your registration type.

Please register!

NAACL 2025

Welcome to 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics

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)* 

<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. 

We propose a novel K -step return estimation method (called K ETCHUP) for Reinforcement Learning (RL)-based knowledge distillation (KD) in text generation tasks. Our idea is to induce a K -step return by using the Bellman Optimality Equation for multiple steps. Theoretical analysis shows that this K -step formulation reduces the variance of the gradient estimates, thus leading to improved RL optimization, especially when the student model size is large. Empirical evaluation on three text generation tasks demonstrates that our approach yields superior performance in both standard task metrics and large language model (LLM)-based evaluation. These results suggest that our K -step return induction offers a promising direction for enhancing RL-based KD in LLM research.

KETCHUP: KK-Step Return Estimation for Sequential Knowledge Distillation

This paper discusses the internal behavior of Transformer language models. Many recent pre-trained models have been reported to exhibit only slight changes in the angular distance between input and output hidden state vectors in the middle Transformer layers, despite a disproportionately large ``jump'' in angular distance occurring in or around the final Transformer layer. To characterize this, we first introduce a quantitative metric for jump strength around the final layer, and then demonstrate its prevalence across many public pre-trained models, as well as its amplification throughout pre-training. Assuming such jumps indicate an undesirable property, we propose a regularizer that penalizes the jump during pre-training, thereby encouraging more balanced capability usage across the middle layers. Empirical evaluations of three model sizes of Llama-based models, trained with our jump-suppressing regularizer (JREG), reveal improved task performance compared to the baseline without altering the model architecture.

Suppressing Final Layer Hidden State Jumps in Transformer Pretraining

With the increasing adoption of Large Language Models (LLMs) and Vision-Language Models (VLMs), rich document analysis technologies for applications like Retrieval-Augmented Generation (RAG) and visual RAG are gaining significant attention. Recent research indicates that using VLMs yields better RAG performance, but processing rich documents remains a challenge since a single page contains large amounts of information. In this paper, we present SCAN (SemantiC Document Layout ANalysis), a novel approach that enhances both textual and visual Retrieval-Augmented Generation (RAG) systems that work with visually rich documents. It is a VLM-friendly approach that identifies document components with appropriate semantic granularity, balancing context preservation with processing efficiency. SCAN uses a coarse-grained semantic approach that divides documents into coherent regions covering contiguous components. We trained the SCAN model by fine-tuning object detection models on an annotated dataset. Our experimental results across English and Japanese datasets demonstrate that applying SCAN improves end-to-end textual RAG performance by up to 9.4 points and visual RAG performance by up to 10.4 points, outperforming conventional approaches and even commercial document processing solutions.

SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation

Recent advancements in LLMs have significantly improved mathematical problem-solving, with models like GPT-4 achieving human-level performance. However, proficiently solving mathematical problems differs fundamentally from effectively teaching mathematics. To bridge this gap, we introduce the Bi-GSM8K benchmark, a bilingual English-Korean dataset enriched with teacher solutions, student solutions, and annotations marking students' initial errors. This dataset is designed to evaluate two core capabilities of LLMs: (1) measuring similarity between student and teacher solutions, and (2) identifying the initial error point in student solutions. Our method achieves high agreement with human judgments, with Pearson 0.89 and Spearman 0.88 on English, and Pearson 0.89 and Spearman 0.87 on Korean. It also offers significantly lower latency and resource usage than commercial APIs, demonstrating strong computational efficiency. In the error detection task, open-source models achieved approximately 86% accuracy, with performance within 10% points of commercial LLMs API, suggesting strong practical potential. Our key contributions include the open-source release of Bi-GSM8K, novel evaluation metrics, and comparative analyses of LLM performance across languages.

Beyond Accuracy: Alignment and Error Detection across Languages in the Bi-GSM8K Math-Teaching Benchmark

In conversation, humans use multimodal cues, such as speech, gestures, and gaze, to manage turn-taking. While linguistic and acoustic features are informative, gestures provide complementary cues for modeling these transitions. To study this, we introduce DnD Gesture++, an extension of the multi-party DnD Gesture corpus enriched with 2,663 semantic gesture annotations spanning iconic, metaphoric, deictic, and discourse types. Using this dataset, we model turn-taking prediction through a Mixture-of-Experts framework integrating text, audio, and gestures. Experiments show that incorporating semantically guided gestures yields consistent performance gains over baselines, demonstrating their complementary role in multimodal turn-taking.

Modeling Turn-Taking with Semantically Informed Gestures

Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets too small, and most benchmarks conflate heuristics with inference. We present FOL-Traces, the first large-scale dataset of programmatically verified reasoning traces, enabling rigorous evaluation of structured logical inference. We also propose two challenging and comprehensive diagnostic tasks---masked operation prediction and step completion---that directly probe syntactic awareness and process fidelity. FOL-Traces serves as a scalable testbed for rigorously studying how models perform structured logical inference. Systematic experiments with 5 reasoning LLMs show that the dataset remains challenging: models only reach around 45.7% accuracy on masked operation prediction and around 27% on two-step completion.

FOL-Traces: Verified First-Order Logic Reasoning Traces at Scale

Large language models suffer from positional biases like the "Lost in the Middle'" (LiM) phenomenon and recency bias, which undermine the performance of long-context retrieval augmented generation. In this work, we investigate the role of rotary position embeddings (RoPE) in this context. Our empirical study confirms the persistence of these biases in modern language models. Drawing on these findings, we introduce Caliope, a training-free calibration framework for modifying RoPE inputs at inference time. Our calibrators yield substantial improvements in specific model-task configurations, revealing complex performance trade-offs between simple needle-in-a-haystack experiments and more demanding cross-chunk reasoning tasks. This work offers a practical mitigation framework and key insights into the nature of positional biases.

Can Calibration of Positional Encodings Enhance Long Context Utilization?

Modern language models excel at factual reasoning but struggle with value diversity: the multiplicity of plausible human perspectives. Tasks such as hate speech or sexism detection expose this limitation, where human disagreement captures the diversity of perspectives that models need to account for, rather than dataset noise. In this paper, we explore whether multi-perspective in-context learning (ICL) can align large language models (LLMs) with this diversity without parameter updates. We evaluate four LLMs on five datasets across three languages (English, Arabic, Italian), considering three label-space representations (aggregated hard, disaggregated hard, and disaggregated soft) and five demonstration selection and ordering strategies. Our multi-perspective approach outperforms standard prompting on aggregated English labels, while disaggregated soft predictions better align with human judgments in Arabic and Italian datasets.These findings highlight the importance of perspective-aware LLMs for reducing bias and polarization, while also revealing the challenges of applying ICL to socially sensitive tasks. We further probe the model faithfulness using XAI, offering insights into how LLMs handle human disagreement.

Seeing All Sides: Multi-Perspective In-Context Learning for Subjective NLP

No. Whilst Multimodal Large Language Models (MLLMs) have been shown to perform very well on general video data, we systematically show that their performance on movies lags behind. This is surprising as MLLMs are increasingly used for movie understanding. To measure the performance of MLLMs on movies, we explore three pillars of movie mastery: movie knowledge, cinematographic knowledge, and critical analysis. Through a combination of quantitative and in-depth qualitative evaluations we identify where MLLMs show promise and, in particular, where they fail. Our findings show that in small-scale settings involving factual knowledge, MLLMs are able to outperform existing methods. However, once cinematographic and critical analysis is required, MLLMs are insufficiently able to extract meaningful information from the visual modality to be able to provide useful insights.

Are Multimodal LLMs Movie Buffs?

Graphical User Interface (GUI) grounding is critical for effective GUI agents. Despite recent progress, key challenges remain: 1) existing grounding models and benchmarks are skewed toward web and mobile environments, neglecting desktop interfaces (especially windows); and 2) grounding capability is assessed using accuracy on a single "best" instruction per UI element. However, users can refer to a UI element in diverse valid ways -- via visual attributes, spatial relations, etc, and a capable grounding model should produce consistent outputs across such variations. Focusing on desktop environments, we introduce GUI Grounding Sensitivity Benchmark, which investigates the model sensitivity to multiple descriptions of the same UI element. We design an automatic pipeline to generate multiple valid instructions per UI element, and develop nuanced data validation methods, as frontier models even hallucinate to produce a single instruction. Evaluation of 12 models reveals they are reasonably sensitive and their performance on existing benchmarks does not reflect their true ability. Building on the insight that a given grounding model struggles more with certain instructions or relations, we introduce the GUI Grounding Diagnosis Agent, which generates challenging instructions using model feedback and iterative refinement. Our agent reports high success rate (upto 84%) in generating instructions that fail the state-of-the-art GUI grounding models.

Downloads

Next from EACL 2026

KETCHUP: KK-Step Return Estimation for Sequential Knowledge Distillation

Similar lecture

On the Impact of Fine-Tuning on Chain-of-Thought Reasoning