Morocco

Understanding user intent is essential for effective planning in conversational assistants, particularly those powered by large language models (LLMs) coordinating multiple agents. However, real-world dialogues are often ambiguous, underspecified, or dynamic, making intent understanding a persistent challenge. Traditional classification-based approaches struggle to generalize in open-ended settings, leading to brittle interpretations and poor downstream planning. We propose RECAP (REwriting Conversations for Agent Planning), a new benchmark designed to evaluate and advance intent rewriting, reframing user-agent dialogues into concise representations of user goals. RECAP captures diverse challenges such as ambiguity, intent drift, vagueness, and mixed-goal conversations. Alongside the dataset, we introduce an LLM-based evaluator that compares planning utility given a user-agent dialogue. Using RECAP, we develop a prompt-based rewriting approach that outperforms baselines, in terms of plan preference. We further demonstrate that fine-tuning two DPO-based rewriters yields additional utility gains. Our results highlight intent rewriting as a critical and tractable component for improving agentic planning in open-domain dialogue systems.

EACL 2026

RECAP: REwriting Conversations for Intent Understanding in Agentic Planning

human study evaluation

intent understanding

llms

agents

query rewriting

planning

benchmarking

fine-tuning

evaluation

dialogue

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

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 ACL 2025". 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 need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

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.

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. 

Evaluating the quality of open-domain chatbots has become increasingly reliant on LLMs acting as automatic judges. However, existing meta-evaluation benchmarks are static, outdated, and lacking in multilingual coverage, limiting their ability to fully capture subtle weaknesses in evaluation. We introduce MEDAL, an automated multi-agent framework for curating more representative and diverse open-domain dialogue evaluation benchmarks. Our approach leverages several LLMs to generate user-chatbot multilingual dialogues, conditioned on varied seed contexts. Then, a state-of-the-art LLM (GPT-4.1) is used for a multidimensional analysis of the performance of the chatbots, uncovering noticeable cross-lingual performance differences. Guided by this large-scale evaluation, we curate a new meta-evaluation multilingual benchmark and human-annotate samples with nuanced quality judgments. This benchmark is then used to assess the ability of several reasoning and non-reasoning LLMs to act as evaluators of open-domain dialogues. Using MEDAL, we uncover that state-of-the-art judges fail to reliably detect nuanced issues such as lack of empathy, common sense, or relevance.

MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators

Massively multilingual language models enable cross-lingual generalization but underperform on low-resource and unseen languages. While adapter-based fine-tuning offers a parameter-efficient solution, training language-specific adapters at scale remains costly. We introduce Typologically Informed Parameter Aggregation (TIPA), a training-free framework that constructs proxy language adapters by aggregating existing ones, weighted by typological similarity. Integrated into the MAD-X architecture, these proxies enable zero-shot cross-lingual transfer without additional training. We evaluate TIPA on five NLP tasks and over 230 languages. TIPA consistently outperforms baselines such as English-only fine-tuning and selecting the typologically closest-language adapter, with the largest gains for languages lacking dedicated adapters. Our results demonstrate that typologically informed aggregation provides a viable alternative to language-specific modules without any training needed.

TIPA: Typologically Informed Parameter Aggregation

Recent multilingual named entity recognition (NER) work has shown that large language models (LLMs) can provide effective synthetic supervision, yet such datasets have mostly appeared as by-products of broader experiments rather than as systematic, reusable resources. We introduce FiNERweb, a dataset-creation pipeline that scales the teacherвЂ“student paradigm to 91 languages and 25 scripts. Building on FineWeb-Edu, our approach trains regression models to identify NER-relevant passages and annotates them with multilingual LLMs, resulting in about 225k passages with 235k distinct entity labels. We train a student model on this dataset to enable the research community to efficiently expand annotations in their desired languages. The regression model for filtering useful NER passages achieves more than 84 F1. We assess annotation quality using LLM-based ratings, which show high faithfulness (3.99/5) and completeness (4.05/5). We further translate the label set into the respective target languages and observe a performance decrease of 0.02-0.09 F1. This result shows that many multilingual models rely heavily on English label prompts and that improved cross-lingual alignment is essential for future work.

FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition

Annotated data scarcity has long hindered progress in dialogue discourse parsing. To fill this gap, we introduce MIMIC, a framework for augmenting discourse-annotated corpora via speaker stylistic transfer using Large Language Models (LLMs). MIMIC rephrases utterances while preserving discourse coherence, using the MASK metric to identify speakers for replacement that enrich structural diversity and the MIRROR method to select substitute speakers who have experienced similar discourse interactions. Experimental results on STAC and Molweni corpora show that parsers trained with MIMIC-augmented data improve both link prediction and relation classification, with consistent gains for underrepresented discourse patterns and in low-resource scenarios.

MIMIC: Multi-party Dialogue Augmentation via Speaker Stylistic Transfer

Deep search, which aims to answer complicated questions requiring searching for and reasoning across multiple documents, is becoming one of the most important agentic use-cases. Yet, it is not scalable to leverage human annotations to collect deep search data due to long and complex exploration trajectories. We propose an agentic pipeline to automatically generate high-quality deep search question answer pairs for a given corpus. Our initial data generator agent is able to produce QA pairs that need multiple rounds of search based on an input document. To further improve the steer-ability of our data generation framework, we 1) add a natural language prompt to specify a level of difficulty; 2) incorporate the execution traces from a task execution agent as feedback to correct undesirable data. Our intrinsic evaluation shows our framework significantly increases the correctness and difficulty of the generated data. Our extrinsic evaluation demonstrates that compared to training with existing large-scale training data, our data improved the trained search agent with >15% gains across in-domain and out-of-domain complex question answering datasets on two model sizes. Analysis shows that our pipeline generates questions that require diverse reasoning strategies.

Steerable Agentic Data Generation for Deep Search with Execution Feedback

Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight emerging challenges in the LLM era, particularly the paradox of choice: the difficulty of attributing performance gains amid diverse base models and training sets in the context of table instruction tuning. We replicate four table LLMs by instruction-tuning three foundation models on four existing datasets, yielding 12 models. We then evaluate these models across 16 table benchmarks. Our study is the first to quantitatively disentangle the effects of training data and base model selection, revealing that base model choice plays a more dominant role than the training data itself. Generalization and reasoning remain challenging, inviting future effort on table modeling. Based on our findings, we share our thoughts on the future directions for table modeling.

What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects

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.

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

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.

Downloads

Next from EACL 2026

MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators

Similar lecture

Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification