Morocco

Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at intermediate layers and then project them back into target-language token spaces in the final layer. From this observation, we hypothesize that this cross-lingual transition is governed by a small and sparse set of dimensions, which occur at consistent indices across the intermediate to final layers. Building on this insight, we introduce a simple, training-free method to identify and manipulate these dimensions, requiring only as few as 50 sentences of either parallel or monolingual data. Experiments on a multilingual generation control task reveal the interpretability of these dimensions, demonstrating that the interventions in these dimensions can switch the output language while preserving semantic content, and that it surpasses the performance of prior neuron-based approaches at a substantially lower cost.

EACL 2026

Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models

language-specific dimensions

model intervention

interpretability and analysis of models for nlp

multilingualism and cross-lingual nlp

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

AAAI 2025

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



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. 

This paper introduces a novel framework for simulating and analyzing how uncooperative behaviors can destabilize or collapse LLM-based multi-agent systems. Our framework includes two key components: (1) a game theory-based taxonomy of uncooperative agent behaviors, addressing a notable gap in the existing literature; and (2) a structured, multi-stage simulation pipeline that dynamically generates and refines uncooperative behaviors as agents' states evolve. We evaluate the framework via a collaborative resource management setting, measuring system stability using metrics such as survival time and resource overuse rate. Empirically, our framework achieves ~96.7% accuracy in generating realistic uncooperative behaviors, validated by human evaluations. Our results reveal a striking contrast: cooperative agents maintain perfect system stability (100% survival over 12 rounds with 0% resource overuse), while any uncooperative behavior can trigger rapid system collapse within 1–7 rounds. We also evaluate LLM-based defense methods, finding they detect some uncooperative behaviors, but some behaviors remain largely undetectable. These gaps highlight how uncooperative agents degrade collective outcomes and underscore the need for more resilient multi-agent systems.

The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems

Venture capital (VC) investors face a large number of investment opportunities but only invest in few of these, with even fewer ending up successful. Early-stage screening of opportunities is often limited by investor bandwidth, demanding tradeoffs between evaluation diligence and number of opportunities assessed. To ease this tradeoff, we introduce DIALECTIC, an LLM-based multi-agent system for startup evaluation. DIALECTIC first gathers factual knowledge about a startup and organizes these facts into a hierarchical question tree. It then synthesizes the facts into natural-language arguments for and against an investment and iteratively critiques and refines these arguments through a simulated debate, which surfaces only the most convincing arguments. Our system also produces numeric decision scores that allow investors to rank and thus efficiently prioritize opportunities. We evaluate DIALECTIC through backtesting on real investment opportunities aggregated from five VC funds, showing that DIALECTIC matches the precision of human VCs in predicting startup success.

DIALECTIC: A Multi-Agent System for Startup Evaluation

With context windows of millions of tokens, Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative to conventional retrieval-augmented generation (RAG). However, it remains unclear whether fine-tuning strategies can improve long-context performance and translate to greater robustness under KV-cache compression techniques. In this work, we investigate which training strategies most effectively enhance LCLMs' ability to identify and use relevant information, as well as enhancing their robustness under KV-cache compression. Our experiments show substantial in-domain improvements: achieving up to +20-point gains over the base model. However, out-of-domain generalization remains task dependent with large variance -- LCLMs excels on finance questions (+9 points), while RAG shows stronger performance on multiple-choice questions (+6 points) over the baseline models. Finally, we show that our fine-tuning approaches bring moderate improvements in robustness under KV-cache compression, with gains varying across tasks.

Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models

As Large Language Models (LLMs) become increasingly integrated into everyday life and information ecosystems, concerns about their implicit biases continue to persist. While prior work has primarily examined socio-demographic and leftвЂ“right political dimensions, little attention has been paid to how LLMs align with broader geopolitical value systems, particularly the democracyвЂ“authoritarianism spectrum. In this paper, we propose a novel methodology to assess such alignment, combining (1) the F-scale, a psychometric tool for measuring authoritarian tendencies, (2) FavScore, a newly introduced metric for evaluating model favorability toward world leaders, and (3) role-model probing to assess which figures are cited as general role models by LLMs. We find that LLMs generally favor democratic values and leaders, but exhibit increased favorability toward authoritarian figures when prompted in Mandarin. Further, models are found to often cite authoritarian figures as role models, even outside explicitly political contexts. These results shed light on ways LLMs may reflect and potentially reinforce global political ideologies, highlighting the importance of evaluating bias beyond conventional socio-political axes.

Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models

Large language models (LLMs) are increasingly adopted for handling structured data, including tabular and relational inputs, despite mostly being pretrained on unstructured text. This raises a key question: how effectively do pretrained representations from language-focused LLMs transfer to tasks involving structured inputs? We address this through controlled experiments using two small open-source LLMs, systematically re-initializing subsets of layers with random weights before fine-tuning on structured datasets and comparing results to unstructured datasets. Our analyses show that, for structured data, most pretrained depth contributes little, with performance often saturating after the first few layers, whereas unstructured tasks benefit more consistently from deeper pretrained representations. Pretraining remains useful mainly in low-resource settings, with its impact diminishing as more training data becomes available.

How Much Pretraining Does Structured Data Need?

Stereotype repositories are critical to assess generative AI model safety, but currently lack adequate global coverage. It is imperative to prioritize targeted expansion, strategically addressing existing deficits, over merely increasing data volume. This work introduces a multilingual stereotype resource covering four sub-Saharan African countries that are severely underrepresented in NLP resources: Ghana, Kenya, Nigeria, and South Africa. By utilizing socioculturally-situated, community-engaged methods, including telephonic surveys moderated in native languages, we establish a reproducible methodology that is sensitive to the region's complex linguistic diversity and traditional orality. By deliberately balancing the sample across diverse ethnic and demographic backgrounds, we ensure broad coverage, resulting in a dataset of 3,534 stereotypes in English and 3,206 stereotypes across 15 native languages.

SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context

We propose a novel self-attention mechanism for document understanding that takes into account text block positions in relative polar coordinate system rather than the Cartesian one. Based on this mechanism, we build DocPolarBERT, a layout-aware BERT model for document understanding that eliminates the need for absolute 2D positional embeddings. Despite being pre-trained on a dataset more than six times smaller than the widely used IIT-CDIP corpus, DocPolarBERT achieves state-of-the-art results. These results demonstrate that a carefully designed attention mechanism can compensate for reduced pre-training data, offering an efficient and effective alternative for document understanding.

DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures

Leaderboards are crucial in the machine learning (ML) domain for benchmarking and tracking progress. However, creating leaderboards traditionally demands significant manual effort. In recent years, efforts have been made to automate leaderboard generation, but existing datasets for this purpose are limited by capturing only the best results from each paper and limited metadata. We present MetaLead, a fully human-annotated ML Leaderboard dataset that captures all experimental results for result transparency and contains extra metadata, such as the result experimental type: baseline, proposed method, or variation of proposed method for experiment-type guided comparisons, and explicitly separates train and test dataset for cross-domain assessment. This enriched structure makes MetaLead a powerful resource for more transparent and nuanced evaluations across ML research. MetaLead dataset and code repository: https://anonymous.4open.science/r/metalead-7CA3

MetaLead: A Comprehensive Human-Curated Leaderboard Dataset for Transparent Reporting of Machine Learning Experiments

We challenge the common assumption that Large Language Models (LLMs) build confidence gradually during reasoning. Instead, we find that conviction is often reached in a discrete ``moment of insight'', characterized by a sudden and sharp increase in an answer's probability---a phenomenon we term a "confidence leap". Leveraging this discovery, we introduce a training-free, model-agnostic early-stopping heuristic that halts generation upon detecting such a leap, significantly reducing the generation length without sacrificing accuracy. We also demonstrate that the reasoning text leading up to this leap is semantically potent and transferable: feeding this partial reasoning to a different model family substantially boosts its performance. This suggests that the "confidence leap" marks a shared, interpretable reasoning milestone, not just a model-specific statistical artifact.

Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer

This paper presents a mechanistic investigation into the ability of large language models (LLMs) to generate contrastive sentiments. We define this task as transforming the sentiment of a given text (e.g., positive to negative) with minimal changes. We identify two core mechanisms: (1) a preservation mechanism that preserves the input sentiment, primarily mediated by specific attention heads, and (2) a sentiment transformation mechanism, which integrates a representation of the target sentiment label with the original valenced words using a circuit containing both MLP and attention layers. Building on these findings, we propose and validate a novel mechanistic intervention. By modifying key attention heads, we successfully steer the LLM toward more effective contrastive generation, significantly increasing the sentiment flip rate without sacrificing distance preservation. Our work not only deepens the understanding of how LLMs perform this task but also introduces a promising new direction for steering LLM behavior through targeted, mechanistic interventions.

Downloads

Next from EACL 2026

The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems

Similar lecture

Enhancing Non-English Capabilities of English-Centric Large Language Models Through Deep Supervision Fine-Tuning