Morocco

We introduce BeDiscovER (Benchmark of Discourse Understanding in the Era of Reasoning Language Models), an up-to-date, comprehensive suite for evaluating the discourse-level knowledge of modern LLMs. BeDiscovER compiles 5 publicly available discourse tasks across discourse lexicon, (multi-)sentential, and documental levels, with in total 52 individual datasets. It covers both extensively studied tasks such as discourse parsing and temporal relation extraction, as well as some novel challenges such as discourse particle disambiguation (e.g., just), and also aggregates a shared-task on Discourse Relation Parsing and Treebanking for multilingual and multi-framework discourse relation classification. We evaluate open-source LLMs: Qwen3 series, DeepSeek-R1, and frontier reasoning model GPT-5-mini on BeDiscovER, and find that state-of-the-art models exhibits strong performance in arithmetic aspect of temporal reasoning, but they struggle with long-dependency reasoning and some subtle semantic and discourse phenomena, such as rhetorical relation classification.

EACL 2026

BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models

discourse understanding

llms

benchmarking

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. <br>
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) <br><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://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>
<br><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 ACL 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.aclweb.org/registration/) first.

**Online Registration Form**: https://acl.swoogo.com/acl2026

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

technical paper

#### *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

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 study structured entity extraction from phone-call transcripts in customer-support and healthcare settings, where annotation is costly, and data access is limited by privacy and consent. Existing methods degrade under disfluencies, interruptions, and speaker overlap, yet large real-call corpora are rarely shareable. We introduce LingVarBench, a benchmark and semantic synthetic data generation pipeline that generates linguistically varied training data via (1) LLM-sampled entity values, (2) curated linguistic verbalization patterns covering diverse disfluencies and entity-specific readout styles, and (3) a value–transcript consistency filter. Using this dataset, DSPy's SIMBA automatically synthesizes and optimizes extraction prompts, reducing manual prompt engineering and targeting robustness to verbal variation. On real customer transcripts, prompts optimized solely on LingVarBench outperform zero-shot baselines and match or closely approach human-tuned prompts for structured entities such as ZIP code, date of birth, and name (F1 approximately 94-95 percent). For subjective questionnaire items, optimized prompts substantially improve over zero-shot performance and approach human-tuned prompts. LingVarBench offers a practical and cost-efficient path to deployment in a direct-answer setting, with real annotations later enabling additional refinement.

LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts

Annual reports communicate corporate performance to stakeholders through dense tables and explanatory text, with rich grounding signals making automated reasoning challenging. Existing QA benchmarks focus on retrieval or single-modality reasoning and rarely require justification for answers with both textual and tabular evidence. We introduce ARQA (Annual Report QA), a benchmark of ~2.5K QA pairs spanning ten fiscal years of automotive enterprise annual reports and three reasoning families — Lookup, Arithmetic, and Insight. Data are produced via a planner–generator pipeline, deterministically verified and recomputed, and fully reviewed by domain experts. We evaluate state-of-the-art instruction-tuned language models on ARQA, showing strong factual retrieval but persistent weaknesses in grounded arithmetic and causal reasoning. We release ARQA and its evaluation toolkit to facilitate research on auditable, evidence-first reasoning over enterprise documents. (https://github.com/RuilongWang/ARQA-Benchmark/)

ARQA: A Benchmark for Grounded Table–Text QA in Enterprise Annual Reports

While large language models (LLMs) excel at dialogue, whether they can adequately parse the structure of conversationвЂ”resolve the reply-to relationship between utterances, or attribute roles like speakers and addresseesвЂ”remains underexplored, especially in multimodal settings. To address this, we introduce a suite of tasks for multimodal conversation understanding and release TV-MMPC, a new human-annotated dataset of conversational roles and threading in television dialogue. Our evaluation reveals that while all multimodal LLMs outperform our heuristic baseline, even the best-performing model we consider experiences a substantial drop in performance when character identities of the conversation are anonymized. Beyond evaluation, we carry out a sociolinguistic analysis of 350,842 utterances in TVQA. We find that while female characters initiate conversations at rates in proportion to their speaking time, they are 1.2 times more likely than men to be cast as an addressee or side-participant, and the presence of side-participants shifts the conversational register from personal to social.

Multimodal Conversation Structure Understanding

Interest in leveraging Large Language Models (LLMs) for emotional support systems motivates the need to understand how these models comprehend and represent emotions internally. While recent works show the presence of emotion concepts in the hidden state representations, it's unclear if the model has a robust representation that is consistent across different datasets. In this paper, we present a unified view to understand emotion representation in LLMs, experimenting with diverse datasets and prompts. We then evaluate the reasoning ability of the models on a complex emotion identification task. We find that LLMs have a common emotion representation in the later layers of the model, and the vectors capturing the direction of emotions extracted from these representations can be interchanged among datasets with minimal impact on performance. Our analysis of reasoning with Chain of Thought (CoT) prompting shows the limits of emotion comprehension. Therefore, despite LLMs implicitly having emotion representations, they are not equally skilled at reasoning with them in complex scenarios. This motivates the need for further research to find new approaches.

A Unified View on Emotion Representation in Large Language Models

Natural language processing (NLP) now shapes many aspects of our world, yet its social benefits are underexplored. This paper surveys work in NLP for Social Good (NLP4SG) across nine domains relevant to global development and risk agendas, summarizing principal tasks and challenges. We also analyze ACL Anthology trends, finding that inclusion and AI harms attract the most research, while domains such as poverty, peacebuilding, and environmental protection remain underexplored. Guided by our review, we outline opportunities for responsible and equitable NLP and conclude with a call for cross-disciplinary partnerships and human-centered approaches to ensure that future NLP advances the public good.

NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment

Turn-taking is a fundamental component of human communication and is signalled through complex cues distributed across lexical, temporal, and prosodic information. Full-duplex models of spoken dialogue integrate these information sources to produce impressive turn-taking behaviour; However, existing evaluations of their turn-taking capabilities do not address which information sources drive their predictions. We present a systematic analysis of the role of lexical-temporal features on the predictability of turn structure by examining PairwiseTurnGPT, a full-duplex model of spoken dialogue transcripts. Through PCA, mixed-effects modelling, and temporal surprisal analysis, we reveal context-dependent patterns: linguistic fluency paradoxically creates overconfidence at intermediate completion points, while turn-shift overlap dominates boundary detection. Our findings uncover where lexical-temporal information suffices and where additional cues become necessary, establishing a deeper understanding of how turn-taking cues are distributed and how to evaluate dialogue systems.

Analysing the role of lexical and temporal information in turn-taking through predictability

Retrieval-augmented generation (RAG) systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggregating them to generate an answer. Efficiently selecting informative documents requires balancing a key trade-off: (i) retrieving broadly enough to capture all the relevant material, and (ii) limiting retrieval to avoid excessive noise and computational cost. We formulate query decomposition and document retrieval in an exploitation-exploration setting, where retrieving one document at a time builds a belief about the utility of a given sub-query and informs the decision to continue exploiting or exploring an alternative. We experiment with a variety of bandit learning methods and demonstrate their effectiveness in dynamically selecting the most informative sub-queries. Our main finding is that estimating document relevance using rank information and human judgments yields a 35% gain in document-level precision, 15% increase in О±-nDCG, and better performance on the downstream task of long-form generation. Code is available on GitHub.

Query Decomposition for RAG: Balancing Exploration-Exploitation

Large language models (LLMs) are increasingly capable of generating functional source code, raising questions about authorship, accountability, and security. While detecting AI-generated code is critical, existing datasets and benchmarks are narrow, typically limited to binary human-machine classification under in-distribution settings. To bridge this gap, we introduce AICD Bench, the most comprehensive benchmark for AI-generated code detection. It spans 2M samples, 77 models across 11 families, and 9 programming languages, including new reasoning models. Beyond scale, AICD Bench introduces three realistic detection tasks: (i) Robust Binary Classification under distribution shifts in language and domain; (ii) Model Family Attribution, grouping generators by architectural lineage; and (iii) Fine-Grained Human-Machine Classification across human, machine, hybrid, and adversarial code. We evaluate neural and classical detectors and show that performance remains far below practical usability, underscoring task difficulty. We release a unified, challenging evaluation suite to drive the next generation of robust approaches for AI-generated code detection

AICD Bench: A Challenging Benchmark for AI-Generated Code Detection

Most evaluation methods like LLM-as-a-judge treat each test example independently, overlooking the potential to learn from previous evaluations. We introduce **Learning While Evaluating** (LWE), a framework that enables evaluators to improve sequentially during testing without parameter updates. LWE maintains an evolving *meta-prompt* that (i) produces sample-specific evaluation instructions and (ii) updates itself using self-generated feedback after each batch. While sequential updating improves performance, processing every sample incurs substantial computational overhead. We therefore propose ***Selective* LWE**, which updates the meta-prompt only for cases where the evaluator is uncertain, focusing computation on the most informative samples. On multimodal pairwise evaluation benchmarks, *Selective* LWE outperforms baselines and achieves comparable accuracy to full sequential updates while significantly reducing token costs.

Becoming Experienced Judges: Selective Test-Time Learning for Evaluators

Conversational information seeking (CIS) systems aim to model the user's information need within the conversational context and retrieve the relevant information. One major approach to modeling the conversational context aims to rewrite the user utterance in the conversation to represent the information need independently. In this work, we hypothesize that breaking down the information of an utterance into multiple queries covering different aspects of the information need can lead to more effective retrieval performance. This is more evident in more complex utterances that require gathering evidence from various information sources, where a single query rewrite or query representation cannot capture the complexity of the utterance. We propose MQ4CS, a multi-aspect query generation and retrieval framework, which uses Large Language Models (LLMs) to break the user utterance into multiple queries. This approach improves retrieval performance, as most utterances benefit from more than one rewritten query. We evaluate MQ4CS on six widely used CIS datasets, showing it outperforms state-of-the-art query rewriting methods. Using MQ4CS, we also construct MASQ, which includes multiple-aspect queries for the six datasets. Fine-tuning the \llama model on MASQ yields significant improvements. We make our code and dataset publicly available.

Downloads

Next from EACL 2026

LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts

Similar lecture

BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models

.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

LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts

Similar lecture

BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models

Downloads