United States

This paper presents an approach to localizing visual answers within continuous medical videos using a multi-step multimodal generation pipeline with the MedGenVidQA dataset. We frame visual answer localization as a multimodal fusion problem, integrating raw video, timestamped ASR transcripts, and VLM-generated scene descriptions into structured contextual blocks, enabling the model to cross-reference spoken commentary against observable physical events. We show that targeted guidance, which forces the model to treat audio transcripts as supplementary hints with observable visual movements, significantly outperforms baseline approaches. It achieves state-of-the-art performance on the test leaderboard, yielding an mIoU of 79.55, alongside IoU@0.3, IoU@0.5, and IoU@0.7 scores of 93.75, 90.00, and 77.50, respectively. Our findings highlight the effectiveness of combining multimodal context fusion with targeted guidance to overcome text bias, establishing a promising approach for achieving the micro-level precision required in the medical domain. We release our code on GitHub at https://github.com/biodatlab/medgenvidqa-lamar.

ACL 2026

LAMAR-2 at MedGenVidQA 2026: Visual Answer Localization in Medical Videos via Multimodal LLM and Context-Augmented Prompting

multimodal language model

visual answer localization

temporal grounding

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.

Registration Required

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

workshop paper

This paper presents a system for Task A of the MedGenVidQA 2026 shared task, which requires simultaneously retrieving relevant PubMed documents and medical videos for 60 consumer health topics. The core contribution is a unified multi-stage pipeline that treats video and document retrieval as complementary rather than independent problems.
 For video retrieval, the system fine-tunes a PubMedBERT bi-encoder on 2,710 MedVidQA training samples using BM25-driven hard negative mining. Video transcripts (833 unique videos) are segmented into overlapping 30-second temporal chunks with a 10-second stride, producing 32,489 indexed chunks. At query time, T5-based query expansion generates enriched queries for BM25 sparse retrieval, while the original query drives FAISS dense retrieval. The two ranked lists are fused via weighted Reciprocal Rank Fusion (RRF, dense weight 0.75, sparse weight 0.25), and a cross-encoder (MiniLM-L-6-v2) re-ranks the top-200 fused candidates to produce the final top-10 videos. For document retrieval, the NCBI PubMed ESearch API is queried using a progressive keyword fallback chain with exponential backoff, ensuring full topic coverage.
 The system achieves a MAP of 0.3898, Recall@10 of 0.8449, and NDCG@10 of 0.1079, with complete 60/60 topic coverage across both retrieval modalities. Key limitations include reliance solely on transcript text for video retrieval (no visual or audio features) and dependence on a live API for document retrieval.

Varja-Dominators at MedGenVidQA 2026: Hybrid Video and Document Retrieval using PubMedBERT, T5 Query Expansion, and Cross-Encoder Re-Ranking

This paper describes the Pride-Boiler system submitted to MedGenVidQA 2026 Shared Task A, which asks for retrieving relevant PubMed articles and medical instructional videos in response to consumer health queries. Our approach pairs Pyserini BM25 retrieval with LLM-driven query rewriting and a corrective self-verification loop inspired by the Corrective Retrieval-Augmented Generation (CRAG) paradigm. Given a consumer query, the pipeline first asks Google Gemini to generate clinically optimized search text, one targeting PubMed abstracts with MeSH terms and clinical synonyms, and another targeting video subtitles with procedural action language. BM25 retrieves a broad candidate pool, and Gemini then scores each candidate against the original query, blending its relevance judgment with the normalized lexical signal. A quality grader assesses the top results: if they are judged insufficient, the pipeline triggers a corrective cycle with reformulated terminology and retries up to three attempts. The entire workflow is orchestrated as a LangGraph state machine. In the official shared task evaluation, Pride-Boiler ranked first among all participating systems on PubMed article retrieval, achieving an nDCG of 0.6532 and MAP of 0.5550, both exceeding the organizer-provided Text-RR baseline. Our performance on video (text) retrieval achieves 0.5304 in MAP and 0.5927 in nDCG, outperforming other systems but falling below that of baseline, indicating the structural limitations of lexical matching over noisy subtitle text. We release the pipeline code to support reproducibility on GitHub at https://github.com/basilll007/BioNLP.

Pride-Boiler at MedGenVidQA 2026: LLM-Augmented BM25 Retrieval with Corrective Self-Verification for Biomedical Evidence Retrieval

Language is often used strategically, particularly in high-stakes, adversarial settings, yet most work
on pragmatics and LLMs centers on cooperative settings. This leaves a gap in the systematic understanding of strategic communication in adversarial settings. To address this, we introduce SDA
(Strategic Dialogue Assessment), a framework grounded in Gricean and game-theoretic pragmatics
to assess strategic use of language. It adapts the ME Game jury function to make it empirically
estimable for analyzing dialogue. Our approach incorporates two key adaptations: a commitmentbased
taxonomy of discourse moves, which provides a finer-grained account of strategic effects,
and the use of estimable proxies grounded in Gricean maxims to operationalize abstract constructs
such as credibility. Together, these adaptations build on discourse theory by treating discourse
as the strategic management of commitments, enabling systematic evaluation of how conversational
moves advance or undermine discourse goals. We further derive three interpretable
metrics—Benefit at Turn ( BAT ), Penalty at Turn ( PAT ), and Normalized Relative Benefit at Turn
( NRBAT )—to quantify the perceived strategic effects of discourse moves. We also present CPD
(the Crooked Path Dataset), an annotated dataset of real courtroom cross-examinations, to demonstrate
the framework's effectiveness. Using these tools, we evaluate a range of LLMs and show that
LLMs generally exhibit limited pragmatic understanding of strategic language. While model size
shows an increase in performance on our metrics, reasoning ability does not help and largely hurts,
introducing overcomplication and internal confusion

Strategic Dialogue Assessment: The Crooked Path to Innocence

Discourse coherence is vital for language understanding but underexplored in low-resource languages. Multimodal cues—gestures, prosody, and visual context—can complement scarce text, yet systematic integration is lacking. We present a pilot study on multimodal discourse coherence in Wolof, introducing 45 videos (6.2 hours), 1,096 utterances, and 1,432 annotated relations across six types. Our fusion model combines textual (mBERT), auditory (Wav2Vec + prosody), and visual (ResNet + pose) features, achieving 52.4 macro F1, surpassing text-only (48.7) and audio-only (35.2) baselines. Audio aids causal relations, visuals support contrast, and we discuss annotation challenges and cross-modal alignment. This work provides a foundation for discourse-aware NLP in low-resource languages.

Modeling Multimodal Discourse Coherence in Low-Resource Languages: Work-in-Progress

Discourse presentation is when speech, writing, or thought (SW&T) attributed to a discourse entity (such as a character in a narrative) is presented within a discourse. Discourse presentations can be generally broken into direct or indirect: direct presentation is when the text quotes the words or thoughts verbatim, whereas in indirect presentation the text expresses the SW&T in the narrator's or writer's own words. Automatically detecting and categorizing discourse presentations supports discourse and narrative analysis and improves attribution for downstream NLP tasks, but detecting indirect discourse presentations remains challenging due to diverse surface forms and subtle perspective shifts. We study detection and categorization of discourse presentations on a corrected version of the Semino & Short's English Narrative SW&TP corpus. We cast the task as five-way clause classification: Direct Speech & Writing, Direct Thought, Indirect Speech & Writing, Indirect Thought, and Narrative (i.e., no discourse presentation). We compare four approaches: (1) CNN; (2) generative baseline (Claude Sonnet 4.6); (3) untuned BERT, and (4) fine-tuned BERT. The CNN baseline achieves 0.43 F1 and exhibits substantial confusion with the Narrative class. Claude achieves 0.68 F1 but performs unevenly across classes and fails to recover Indirect Thought. BERT achieves 0.81 F1 overall but struggles on indirect categories. The fine-tuning BERT yields strong performance (0.88 F1), with remaining errors concentrated in Indirect Speech & Writing (F1 = 0.60). We release our code and the corrected dataset to support reproducibility. To our knowledge, this is the first time computational approaches have been evaluated across the full range of SW&TP discourse presentation types.

Baselines for Detection and Classification of Discourse Presentation in English Narrative

The relations connecting propositions in discourse such as cause (A because B) or concession (A although B) are a subject of intense interest in Computational Linguistics and Pragmatics, but challenging to study and compare across languages. Recent progress in standardizing discourse relation inventories across datasets offers the potential to facilitate such studies, but is hindered by the complexity of relevant data and the lack of easily accessible interfaces to analyze it. In this paper we present DiscoExplorer, a new open source web interface, capable of running on local computers, which we use to make datasets from the DISRPT Shared Task on discourse relation classification publicly available, covering 16 different languages. We present the query language, search and visualization facilities for relations and signaling devices such as connectives, as well as some example studies.

DiscoExplorer: An Open Interface for the Study of Multilingual Discourse Relations

Training Large Language Models (LLMs) relies predominantly on written, curated corpora, which may limit their reliability on spontaneous speech. Oral language exhibits real-time planning markers — filled pauses, repetitions, false starts, and vowel lengthenings — that modulate epistemic commitment. This pilot study investigates how such disfluencies affect the alignment between LLM confidence and a discourse-pragmatic uncertainty proxy in a Portuguese model (Llama-3.1-8B-Instruct). Using a benchmark of 344 turns from the Roda Viva corpus, we contrast faithful Conversation Analysis transcriptions with sanitized versions and combine binned divergence metrics (ECE, OE) with rank correlation and multivariate regression analyses. We find that model confidence is overwhelmingly driven by a surface feature — turn length (${\beta_{\text{std}}} = +14.47, p < 0.001$) — rather than by pragmatic markers of uncertainty (${\beta_{\text{oral}}} = -3.09, {\beta_{\text{hedges}}} = -0.97$, both non-significant; $R^2 = 0.29$). After controlling for length, residual effects of disfluency markers align in the human-expected direction but are dwarfed by length bias. We argue that this surface-feature dominance subsumes the pragmatic blindness phenomenon and explains the substantial divergence observed via ECE (41.95) and OE (4.29) between faithful and sanitized conditions.

Speech Disfluencies and LLM Confidence: Length Bias and Pragmatic Insensitivity in Brazilian Portuguese

Recent work representing discourse relations such as "cause" or "concession" in the framework of eRST has connected hierarchical discourse parsing to explicit connectives, such as 'because' or 'although', bringing the framework closer to lexicalized shallow parsing in the tradition of PDTB. However, while PDTB postulates implicit, unexpressed connectives (i.e. an implied 'although' etc.), no such devices are recognized in eRST, and consequently next to nothing is known about the relationship between PDTB-style implicit connectives and eRST-style discourse graphs. In this paper we propose and evaluate an algorithm to align eRST data, which already indicates explicit connectives, to implicit connective annotations following the PDTB guidelines. We also conduct the first evaluation of the relationship between hierarchical RST-style relations and PDTB implicit connectives.

DM Doppelgangers: Implicit Connectives as eRST Signals

In this paper, we present a descriptive corpus analysis of bridging anaphora across 16 genres of English, leveraging the multi-genre GUMBridge corpus for varieties of bridging anaphora. We begin our investigation by examining the distribution of bridging instances by sub-varieties and across genres, finding that spoken genres have less bridging instances than written ones. We then investigate the linguistic environments of bridging anaphora and their corresponding associative antecedents in the underlying data of the corpus, examining both categorical features (entity type, part of speech, syntactic dependency relations) and numeric features (mention length, cluster size, salience, and distance between the bridging anaphor and antecedent). We find bridging anaphora have a tendency to be shorter and are more often definite, and bridging antecedents show tendency to be more salient than other entities. Finally, we analyze how several of the numeric features of bridging environments vary by genre, finding consistency across genres for observed trends in the environments of bridging anaphora and antecedents.

What's in a Bridge?: A Descriptive, Multi-Genre Analysis of the GUMBridge Corpus for Varieties of Bridging Anaphora

Crowd-sourcing implicit discourse relations has been shown to yield a variety of plausible interpretations, but also to be prone to annotation errors. In this study, we apply the dataset cartography technique (Swayamdipta et al., 2020) to implicit discourse relations. We find that error identification via low confidence is infeasible for IDRR datasets; 
however, high confidence in models coincides with strong textual heuristics and with high item-wise agreement, pointing to shortcut use by models and, partly, by crowd workers. Balancing out this factor is required to ensure robust IDRR learning and evaluation.

Downloads

Next from ACL 2026

Varja-Dominators at MedGenVidQA 2026: Hybrid Video and Document Retrieval using PubMedBERT, T5 Query Expansion, and Cross-Encoder Re-Ranking

Similar lecture

Overview of the MedGenVidQA 2026 Shared Task on Medical Generative Video Question Answering

.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 ACL 2026

Varja-Dominators at MedGenVidQA 2026: Hybrid Video and Document Retrieval using PubMedBERT, T5 Query Expansion, and Cross-Encoder Re-Ranking

Similar lecture

Overview of the MedGenVidQA 2026 Shared Task on Medical Generative Video Question Answering

Downloads