Morocco

Multi-hop visual question generation (VQG) seeks to create coherent, fluent, and contextually rich questions by integrating knowledge from a structured knowledge graph (KG) with information inferred from image pairs, where at least one reasoning step involves a visual relationship between the images. Traditional supervised QG methods which rely on token-level alignment with fixed gold labels struggle to capture diverse valid question formulations. We propose M3RQG (M ultimodal M ulti-hop M ulti-decoder R etrieval-augmented Q uestion G eneration), a model-agnostic framework that integrates multimodal inputs (images, KG facts) with a multi-decoder architecture to optimize for multiple labels per sample to design multi-hop questions. M3RQG addresses these challenges: (1) generating meaningful visually-grounded questions given a pair of images, (2) generating rich questions that require multi-hop reasoning across images and KG facts, and (3) integrating diverse question labels during fine-tuning. We extend the WebQA dataset with multi-hop questions generated by GPT-4V and Gemini, resulting in two complementary silver labels per sample. Our approach integrates retrieval-augmented generation (RAG) for accessing external knowledge, a PPO objective with ROUGE-based rewards to prioritize structural correctness, and a named entity overlap loss to improve factual accuracy. Experiments across BART, Phi-3.5, and LLaVA backbones demonstrate significant improvements in fluency, reasoning depth, and relevance. We release our code and dataset to facilitate future research.

EACL 2026

Learning to Ask: Multi-Decoder Fine-Tuning for Multi-Hop Visual Question Generation with External Knowledge

generation

nlp applications

information extraction

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

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. 

Speculative decoding (SD) has proven effective for accelerating LLM inference by quickly generating draft tokens and verifying them in parallel. However, SD remains largely unexplored for Large Vision-Language Models (LVLMs), which extend LLMs to process both image and text prompts. To address this gap, we benchmark existing inference methods with small draft models on 11 datasets across diverse input scenarios and observe scenario-specific performance fluctuations. Motivated by these findings, we propose **Test-time Adaptive Batched Ensemble Drafting (TABED)**, which dynamically ensembles multiple drafts obtained via batch inference by leveraging deviations from past ground truths available in the SD setting. The dynamic ensemble method achieves an average robust walltime speedup of 1.74Г— over autoregressive decoding and a 5% improvement over single drafting methods, while remaining training-free and keeping ensembling costs negligible through parameter sharing. With its plug-and-play compatibility, we further enhance TABED by integrating advanced verification and alternative drafting methods.

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs

Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple prompting strategies have shown success on factual questions, they frequently fail on inferential ones that require reasoning beyond direct text extraction. We hypothesize that asking a model to first reason about what specific information is missing provides a more reliable, implicit signal for assessing overall sufficiency. To this end, we propose a structured Identify-then-Verify framework for robust sufficiency modeling. Our method first generates multiple hypotheses about missing information and establishes a semantic consensus. It then performs a critical verification step, forcing the model to re-examine the source text to confirm whether this information is truly absent. We evaluate our method against established baselines across a diverse suite of datasets, including multi-hop and factual QA. The results demonstrate that by forcing the model to justify its claims about missing information, our framework produces a more accurate sufficiency judgment while detailing any information gaps.

Knowing What's Missing: Assessing Information Sufficiency in Question Answering

A cornerstone of machine learning evaluation is the (often hidden) assumption that model and human responses are reliable enough to evaluate models against unitary, authoritative, ``gold standard'' data, via simple metrics such as accuracy, precision, and recall. The generative AI revolution would seem to explode this assumption, given the critical role stochastic inference plays. Yet, in spite of public demand for more transparency in AI---along with strong evidence that humans are unreliable judges---estimates of model reliability are conventionally based on, at most, a few output responses per input item. We adapt a method, previously used to evaluate the reliability of various metrics and estimators for machine learning evaluation, to determine whether an (existing or planned) dataset has enough responses per item to assure reliable null hypothesis statistical testing. We show that, for many common metrics, collecting even 5-10 responses per item (from each model and team of human evaluators) is not sufficient. We apply our methods to several of the very few extant gold standard test sets with multiple disaggregated responses per item and show that even these datasets lack enough responses per item. We show how our methods can help AI researchers make better decisions about how to collect data for AI evaluation.

How Many Ratings per Item are Necessary for Reliable Significance Testing?

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, and LLM-based agents further extend these abilities to various practical workflows. While recent progress shows that multi-agent systems (MAS) can outperform single agents by coordinating specialized roles, designing effective MAS remains difficult due to prompt sensitivity and the compounded instability MAS creates. To cope with the challenge, recent efforts in automated prompt design have reduced manual effort. However, multi-agent prompt optimization remains largely unexplored. Challenges like exponentially expanding search space and ambiguous credit assignment together make systematic design intractable without principled methods. Therefore, we introduce Multi-Agent PRompt Optimization (MAPRO), a four-stage framework that first formulates MAS prompt optimization as a \textit{Maximum a Posteriori} (MAP) inference problem and solves it using a language-guided variant of max-product belief propagation algorithm. To address credit assignment and updates the system iteratively, MAPRO employs a topology-aware refinement mechanism that integrates execution feedback and downstream blames to selectively update agent prompts. Through this process, MAPRO progressively converges to a coordinated set of agent-specific prompt policies. Across benchmarks in various tasks, MAPRO achieves state-of-the-art performance, consistently surpassing manually engineered baselines and recent automated alternatives. Beyond performance, our MAP-based formulation also delivers general guidelines for building more reliable and principled multi-agent systems in the future.

MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference

Large language models (LLMs) have achieved impressive success across many NLP tasks, yet implicit discourse relation classification (IDRC) is still dominated by encoder-only pre-trained language models such as RoBERTa. This may be due to earlier reports that ChatGPT performs poorly on IDRC in zero-shot settings. In this paper, we show that fine-tuned LLMs can perform on par with, or even better than, existing encoder-based approaches. Nevertheless, we find that LLMs alone struggle to capture subtle lexical relations between arguments for the task. To address this, we propose a two-step strategy that enriches arguments with explicit lexical-level semantic cues before fine-tuning. Experiments demonstrate substantial gains, particularly in cross-domain scenarios, with F1 scores improved by more than 10 points compared to strong baselines.

Linguistic Cues for LLM-based Implicit Discourse Relation Classification

The ability to generate SPARQL queries from natural language questions is crucial for ensuring efficient and accurate retrieval of structured data from knowledge graphs (KG). While large language models (LLMs) have been widely adopted for SPARQL query generation, they are often susceptible to hallucinations and out-of-distribution errors when generating KG elements, such as Uniform Resource Identifiers (URIs), based on opaque internal parametric knowledge. We propose PGMR (Post-Generation Memory Retrieval), a modular framework where the LLM produces an intermediate query using natural language placeholders for URIs, and a non-parametric memory module is subsequently employed to retrieve and resolve the correct KG URIs. PGMR significantly enhances query correctness (SQM) across various LLMs, datasets, and distribution shifts, while achieving the near-complete suppression of URI hallucinations. Critically, we demonstrate PGMR's superior safety and robustness: a retrieval confidence threshold enables PGMR to effectively refuse to answer queries that lack support, and the retriever proves highly resilient to memory noise, maintaining strong performance even when the non-parametric memory size is scaled up to 9 times with irrelevant, distracting entities.

Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval

Large Language Model (LLM) hallucinations are usually treated as defects of the model or its decoding strategy. Drawing on classical linguistics, we argue that a query's form can also shape a listener's (and model's) response. We operationalize this insight by constructing a 22-dimension query feature vector covering clause complexity, lexical rarity, and anaphora, negation, answerability, and intention grounding, all known to affect human comprehension. Using 369,837 real-world queries, we ask: Are there certain types of queries that make hallucination more likely? A large-scale analysis reveals a consistent "risk landscape": certain features such as deep clause nesting and underspecification align with higher hallucination propensity. In contrast, clear intention grounding and answerability align with lower hallucination rates. Others, including domain specificity, show mixed, dataset- and model-dependent effects. Thus, these findings establish an empirically observable query-feature representation correlated with hallucination risk, paving the way for guided query rewriting and future intervention studies.

What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance

As large language models (LLMs) are increasingly deployed as multilingual services, keeping their factual knowledge accurate across languages has become both essential and challenging. However, most of the existing knowledge editing (KE) methods are static, in that they update parameters offline for given accumulated edits of knowledge, and are struggling to effectively propagate edits in one language to others, while avoiding side effects. To mitigate this issue, we propose **CLICKER**, a KE method with stepwise reasoning that dynamically retrieves only knowledge relevant to a given query and then edit, while maintaining cross-lingual consistency through: (1) relevance-aware knowledge retrieval, (2) on-demand in-context KE, and (3) language alignment of the outputs. To rigorously evaluate the locality of edits in cross-lingual KE, we develop **Multi-CounterFact** dataset that contain many semantically-similar but irrelevant prompts for the edit. Experiments on Multi-CounterFact and MzsRE with both open- and closed-source LLMs confirmed that CLICKER effectively localizes edits and resolves cross-lingual inconsistencies, outperforming dynamic KE baselines.

CLICKER: Cross-Lingual Knowledge Editing via In-Context Learning with Adaptive Stepwise Reasoning

Multi-agent debate – multiple instances of large language models discussing problems in turn-based interaction – has shown promise for solving knowledge and reasoning tasks. However, these methods show limitations when solving complex problems that require longer reasoning chains. We analyze how multi-agent debate drifts away from the initial problem over multiple turns, thus harming task performance. We define this phenomenon as problem drift and quantify its presence across ten tasks (i.e., three generative, three knowledge, three reasoning, and one instruction-following task). We find that generative tasks drift often due to the subjectivity of the answer space (76-89%), compared to high-complexity tasks (7-21%). To identify the reasons, eight human experts analyze 170 multi-agent debates suffering from problem drift. We find the most common issues related to this drift are the lack of progress (35% of cases), low-quality feedback (26% of cases), and a lack of clarity (25% of cases). We propose DRIFTJudge, an LLM-as-a-judge method, as a first baseline to detect problem drift. We also propose DRIFTPolicy, which mitigates 31% of problem drift cases. Our study is a step toward understanding a key limitation of multi-agent debate, highlighting why longer debates can harm task performance and how problem drift could be addressed.

Stay Focused: Problem Drift in Multi-Agent Debate

We investigate the robustness of fine-tuned Large Language Models (LLMs) for the task of Natural Language Inference (NLI), finding that the in-distribution gains from fine-tuning correspond to a large drop in out-of-distribution (OOD) performance. Despite the widespread use of closed-source LLMs, there are no robustness mitigation methods that work under their API fine-tuning constraints. Existing methods to improve robustness typically require changing the fine-tuning process or large-scale data augmentation, methods that are infeasible or cost prohibitive for closed-source models. To address this, we propose strategically selecting the NLI fine-tuning data, prioritising more complex examples or replacing existing training examples with LLM-generated data. Prioritising more complex training examples improves performance on challenging OOD NLI datasets, while training with synthetic data leads to substantial improvements on easier OOD datasets. We find that synthetic examples are often too simple, and by prompting LLMs to create more complex synthetic data we can improve performance on both easy and challenging OOD datasets. Finally, we show that recent autoregressive LLMs are substantially more robust to distributional shifts compared to encoder models, and should be a preferred baseline for future research.

Downloads

Next from EACL 2026

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs

Similar lecture

Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps