Morocco

Modern large language model (LLM) systems frequently route inputs to specialized experts to improve accuracy, efficiency, and robustness. Routers determine which expert to activate based on the input, typically represented as a single vector. The construction of this vector limits the distinctions the router can make. Prior work rarely isolates how this vector representation affects routing behavior. We isolate the role of the representation by holding the routing pipeline fixed and vary only how this representation is formed in multilingual settings. We find that representation choice systematically reshapes the available routing partitions. In multilingual routing settings, the routers single-vector input often only encodes shallow features (language/format), resulting in domains that are organized by these features rather than by topic. To mitigate this, we introduce Funnel pooling, a lightweight trainable in-model readout that constructs the routing vector directly from token-level hidden states and does not require a separate embedding encoder. Funnel pooling reduces language and source-dataset driven clustering and results in more topic-aligned domains. Despite this shift, downstream routing performance remains competitive with introducing only a minor inference overhead.

EACL 2026

What the Router Sees Matters: Funnel Pooling for Fast, Content Driven Expert Routing

hidden-state pooling

llm-routing

multilingual embeddings

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

ACL 2022

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

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. 

Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains unclear. Robust causal reasoning is fundamental to solving complex high-level reasoning tasks, yet existing benchmarks often include a mixture of reasoning questions, and VLMs can frequently exploit object recognition and activity identification as shortcuts to arrive at the correct answers, making it challenging to truly assess their causal reasoning abilities. To bridge this gap, we introduce VQA-Causal and VCR-Causal, two new benchmarks specifically designed to isolate and rigorously evaluate VLMs' causal reasoning abilities. Our findings reveal that while VLMs excel in object and activity recognition, they perform poorly on causal reasoning tasks, often only marginally surpassing random guessing. Further analysis suggests that this limitation stems from a severe lack of causal expressions in widely used training datasets, where causal relationships are rarely explicitly conveyed. We additionally explore fine-tuning strategies with hard negative cases, showing that targeted fine-tuning can improve model's causal reasoning while maintaining generalization and downstream performance. Our study highlights a key gap in current VLMs and lays the groundwork for future work on causal understanding.

What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning

Large language models (LLMs) are highly sensitive to subtle changes in prompt phrasing, posing challenges for reliable auditing. Prior methods often apply unconstrained prompt paraphrasing, which risk missing linguistic and demographic factors that shape authentic user interactions. We introduce AUGMENT (Automated User-Grounded Modeling and Evaluation of Natural Language Transformations), a framework for generating controlled paraphrases, grounded in user behaviors. AUGMENT leverages linguistically informed rules and enforces quality through checks on instruction adherence, semantic similarity, and realism, ensuring paraphrases are both reliable and meaningful for auditing. Through case studies on the BBQ and MMLU datasets, we show that controlled paraphrases uncover systematic weaknesses that remain obscured under unconstrained variation. These results highlight the value of the AUGMENT framework for reliable auditing.

Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework

Judeo-Arabic refers to Arabic variants historically spoken by Jewish communities across the Arab world, primarily during the Middle Ages. Unlike standard Arabic, it is written in Hebrew script by Jewish writers and for Jewish audiences. Transliterating Judeo-Arabic into Arabic script is challenging due to ambiguous letter mappings, inconsistent orthographic conventions, and frequent code-switching into Hebrew and Aramaic. In this paper, we introduce a two-step approach to automatically transliterate Judeo-Arabic into Arabic script: simple character-level mapping followed by post-correction to address grammatical and orthographic errors. We also present the first benchmark evaluation of LLMs on this task. Finally, we show that transliteration enables Arabic NLP tools to perform morphosyntactic tagging and machine translation, which would have not been feasible on the original texts.

A Tale of Two Scripts: Transliteration and Post-Correction for Judeo-Arabic

This paper presents an evaluation framework for probing large language models' linguistic knowledge of Indigenous languages of the Americas using zero- and few-shot prompting. The framework consists of three tasks: (1) language identification, (2) cloze completion of Spanish sentences supported by Indigenous-language translations, and (3) grammatical feature classification. We evaluate models from five major families (GPT, Gemini, DeepSeek, Qwen, and LLaMA) on 13 Indigenous languages, including Bribri, Guarani, and Nahuatl. The results show substantial variation across both languages and model families. While a small number of model-language combinations demonstrate consistently stronger performance across tasks, many others perform near chance, highlighting persistent gaps in current models' abilities on Indigenous languages.

Measuring Linguistic Competence of LLMs on Indigenous Languages of the Americas

Recent advances in multimodal and speech-native large language models (LLMs) have delivered impressive speech recognition, translation, understanding, and question-answering capabilities for high-resource languages. However, African languages and non-native French or English accents remain dramatically underrepresented in benchmarks limiting the understanding and applicability of leading LLMs for millions of francophone and anglophone users in low-resource settings. We presents AfriVox, an open-source benchmark (including novel domain-specific and unscripted datasets) across 20 African languages, African-accented French, Arabic, and 100+ African English accents, contrasting leading multimodal speech LLMs with traditional unimodal automatic speech transcription (ASR) and translation (AST) models. Our analysis reveals significant language coverage variation, surprising LLM translation performance gains (e.g. Gemini), robustness concerns with unscripted speech, and substantial performance disparities for "supported" African languages. We profile the strengths, limitations, and language support of each model, and conduct the first targeted fine-tuning of a modern speech LLM (Qwen2.5-Omni) for three Nigerian languages, exceeding SOTA, and achieving up to 54% relative WER reduction and significant BLEU gains, offering practical guidance for implementers seeking to serve local language users.

AfriVox: Probing Multilingual and Accent Robustness of Speech LLMs

Test-time compute methods can significantly improve the reasoning capabilities and problem-solving accuracy of large language models (LLMs). However, these approaches require substantially more computational resources, with most compute wasted on exploring low-diversity branches where the model already exhibits high confidence. We observe that a small subset of uncertain reasoning steps has a disproportionately large impact on final prediction accuracy, and branching at these critical junctures tends to yield more diverse and higher-quality candidate reasoning steps. We propose Entropy-Gated Branching (EGB), which branches only at high-uncertainty steps and prunes expansions with a lightweight verifier. On mathematical and financial reasoning benchmarks, EGB improves accuracy by 22.6% over standard inference while operating 31%-75% faster across math benchmarks than test-time beam search with higher performance. Our results show that dynamic resource allocation during inference can substantially improve both efficiency and effectiveness, offering a more scalable pathway to enhanced LLM reasoning capabilities.

Entropy-Gated Branching for Efficient Test-Time Reasoning

Large language models are being rapidly applied across many fields such as healthcare, finance, transportation, and energy, among many others. These applications often involve analyzing time-series data alongside contextual information in the form of natural language to support informed decisions. However, current time-series models are limited in their ability to perform reasoning that involves both time-series and their textual content. In this work, we address this gap by introducing Chat-TS, a large language model (LLM) based framework designed to support reasoning over time series and textual data. Unlike traditional models, Chat-TS integrates time-series tokens into LLMs' vocabulary, enhancing its reasoning ability over both modalities without compromising core natural language capabilities. To support learning and evaluation, we contribute new datasets: the TS Instruct Training Dataset (pairing diverse time-series data with relevant text instructions and responses for instruction tuning), the TS Instruct Question and Answer (QA) Gold Dataset (multiple-choice questions to evaluate multimodal reasoning), and a TS Instruct Quantitative Probing Set (a small subset of TS Instruct QA reasoning tasks alongside math and decision-making questions for LLM evaluation). We design a training strategy to preserve the inherent reasoning capabilities of LLMs while augmenting them for time-series reasoning. Experiments show that Chat-TS achieves state-of-the-art performance in multimodal reasoning tasks by maintaining strong natural language proficiency while improving time-series reasoning.

Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data

Quantitative text analysis relies on high-quality corpora, but keyword-based collection often retrieves irrelevant material, undermining validity. We show that active learning with a transformer-based classifier can iteratively refine corpora by excluding irrelevant documents, prompting researchers to clarify inclusion criteria and address edge cases. Applied to German newspaper articles on depression and schizophrenia, this approach improves construct validity and reduces labeling effort. The document relevance classifiers reached an F1-score of 0.8 with just 100–150 labeled snippets, with further gains from tuning, outperforming both random sampling and a weakly supervised sampling baseline. Filtering non-medical articles further had little effect on downstream depression stigmatization measures but increased schizophrenia stigmatization. Active learning thus enables efficient corpus validation and clearer concept boundaries with minimal preprocessing. The source code is publicly available at https://github.com/jakobstgl/active-learning-corpus-refinement.

Active Learning for Corpus Refinement: Cost-Effective Preprocessing to Improve Validity of Applied Quantitative Text Analysis

Developing a machine translation (MT) system requires a considerable amount of high-quality parallel data, which is often limited for low-resource languages. This paper explores the use of synthetic data for training an LLM-based MT system in the English-to-Basque direction. Using Basque monolingual corpora as a starting point, we apply back-translation to generate parallel corpora, taking advantage of the fact that current LLMs do not translate well from English to Basque, but they yield an acceptable performance in the reverse direction. We conduct experiments in a multi-stage approach, from a simple Supervised Fine-tuning (SFT) step, to preference learning with the Direct Preference Optimization (DPO) technique. We then evaluate the approach with both automatic metrics and manual assessment. Experimental results suggest that for this task, SFT brings a clear improvement in translation quality, while DPO only yields marginal enhancement.

Machine Translation for Low-Resource Languages through Monolingual Data and LLM: A Case Study of English-to-Basque

Existing linguistic knowledge bases such as URIEL+ provide valuable geographic, genetic and typological distances for cross-lingual transfer but suffer from two key limitations. First, their one-size-fits-all vector representations are ill-suited to the diverse structures of linguistic data. Second, they lack a principled method for aggregating these signals into a single, comprehensive score. In this paper, we address these gaps by introducing a framework for type-matched language distances. We propose novel, structure-aware representations for each distance type: speaker-weighted distributions for geography, hyperbolic embeddings for genealogy, and a latent variables model for typology. We unify these signals into a robust, task-agnostic composite distance. Across multiple zero-shot transfer benchmarks, we demonstrate that our representations significantly improve transfer performance when the distance type is relevant to the task, while our composite distance yields gains in most tasks.

Downloads

Next from EACL 2026

What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning

Similar lecture

StableMoE: Stable Routing Strategy for Mixture of Experts

.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

What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning

Similar lecture

StableMoE: Stable Routing Strategy for Mixture of Experts

Downloads