United States

Large Language Models such as GPT-4o and GPT-5 achieve strong zero-shot performance on biomedical claim verification, but cost and opacity limit scalable use. We fine-tune three small LLMs; Phi-3-mini (3.8B), Qwen2.5-3B, and Mistral-7B; via QLoRA on SciFact and HealthVer, providing the first study of QLoRA models against GPT-4o and fine-tuned BioLinkBERT encoders. Mistral-7B QLoRA achieves higher F1 than both GPT-4o and GPT-5 (up to 12% gain) at 44.5x lower cost using just 1,008 training examples, representing a compelling cost-quality trade-off. We conduct extensive in-domain and cross-domain evaluation: models trained on SciFact tested on HealthVer and vice versa, at matched sizes to isolate dataset structure from data quantity. We identify a previously unreported structural artifact in SciFact that inflates in-domain scores, and show through bidirectional out-of-domain evaluation that training on structurally sound data enables robust cross-domain transfer. We plan to release all code and adapter checkpoints.

ACL 2026

Small LLMs for Biomedical Claim Verification: Cost-Effective Fine-Tuning, Structural Dataset Shortcuts, and Cross-Domain Generalization

cross domain evaluation

qlora finetuning

biomedical claim verification

### 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)

workshop paper

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. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/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://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</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 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

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

Reliable biomedical and clinical retrieval requires more than strong ranking performance: it requires a practical way to find systematic model failures and curate the training evidence needed to correct them.
 Late-interaction models such as ColBERT provide a first solution thanks to the interpretable token-level interaction scores they expose between document and query tokens.
 Yet this interpretability is shallow: it explains a particular document--query pairwise score, but does not reveal whether the model has learned a clinical concept in a stable, reusable, and context-sensitive way across diverse expressions.
 As a result, these scores provide limited support for diagnosing misunderstandings, identifying irreasonably distant biomedical concepts, or deciding what additional data or feedback is needed to address this.
 In this short position paper, we propose Diagnosable ColBERT, a framework that aligns ColBERT token embeddings to a reference latent space grounded in clinical knowledge and expert-provided conceptual similarity constraints.
 This alignment turns document encodings into inspectable evidence of what the model appears to understand, enabling more direct error diagnosis and more principled data curation without relying on large batteries of diagnostic queries.

Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference

Clinical Concept Normalization is essential for clinical research applications involving trial protocols, such as patient-trial matching. Existing approaches focus heavily on specific domains and need large, annotated datasets. To address these challenges, we propose CENT, a context engineering framework that combines semantic matching for candidate retrieval and Large Language Model (LLM) prompting for disambiguation. We applied CENT on a publicly available dataset of procedures normalized to Current Procedural Terminology (CPT) concepts and evaluated the framework using both binary and hierarchical metrics that take into account hierarchical characteristics of predicted codes. CENT achieves superior performance on clinical procedures normalization in both binary and hierarchical metrics compared to semantic matching or LLM-only approaches, without requiring fine-tuning. Advanced prompt strategies, including Chain-of-Thought and Tree-of-Thoughts, achieve high performance at practical cost. We further applied CENT to predict codes in two clinical protocol-derived datasets to validate its performance on noisy procedure texts. CENT is scalable and adaptable for normalization across diverse clinical vocabularies in real-world clinical applications.

CENT: Context Engineering Framework for Normalization of Clinical Trial Procedures

Retrieval-augmented generation (RAG) reduces hallucination in large language models by grounding outputs in retrieved evidence, but it does not guarantee that the resulting citations support the associated claims.
 We present VERICITE, a framework for evaluating citation faithfulness in retrieval-augmented medical QA.
 Our system retrieves PubMed abstracts via the NCBI E-Utilities API, prompts LLMs to generate answers with inline citations, and verifies each citation at the sentence level using a DeBERTa-v3-large NLI model.
 We evaluate four LLMs on 500 BioASQ questions at retrieval depths of 3 and 5, with extended experiments up to k = 15 and an oracle setting with gold standard documents.
 Only 27–41% of citation pairs are supported at the sentence level at retrieval depths of 3 and 5, with support rates declining further at larger k.
 Under the oracle condition, answer quality improves, but citation faithfulness does not substantially improve, suggesting that generation-side citation behavior contributes substantially to unfaithful citations.

VERICITE: Evaluating Sentence-Level Citation Faithfulness in Retrieval-Augmented Medical Question Answering

Biomedical abstracts play a critical role in downstream NLP applications, such as information retrieval, biocuration, and biomedical knowledge discovery. However, a non-trivial number of biomedical articles do not have abstracts, diminishing the utility of these articles for downstream tasks. We propose DPR-BAG (Divide, Prompt, and Refine for Biomedical Abstract Generation), a training-free, zero-shot framework that generates coherent and factually grounded abstracts for biomedical articles with full text but no abstract. DPR-BAG decomposes full-text documents into structured rhetorical facets following the Background-Objective-Methods-Results-Conclusions (BOMRC) schema, performs parallel LLM-based summarization for each facet, and applies a final refinement stage to restore global discourse coherence. On PMC-MAD, a distribution-aligned dataset of 46,309 biomedical articles, DPR-BAG improves abstractive novelty over strong extractive and fine-tuned baselines, while maintaining factual consistency. Our ablation study reveals a counterintuitive finding: increasing prompt complexity or explicitly injecting entity-level guidance can degrade factual alignment, highlighting the importance of controlled prompting strategies. These findings underscore the potential of training-free, structure-aware frameworks for scalable biomedical abstract generation in low-resource settings. Our data and code are available at https://huggingface.co/datasets/pmc-mad/PMC-MAD and https://github.com/ScienceNLP-Lab/MultiTagger-v2/tree/main/DPR-BAG.

Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation

Despite advances in information extraction driven by deep learning and large language models, performance gaps remain in highly specialized biomedical fields, where domain-specific complexity poses challenges for generalist models.
 In this work, we focus on the domain of autoimmunity where the main entities of interest are autoimmune diseases, autoantibodies (i.e. molecules that may mark or cause these diseases), their molecular targets, their location in the body, and the associated clinical signs. 
 Herein, we present AAbAAC (AutoAntibodies and Autoimmunity Annotated Corpus), a corpus of 115 abstracts selected from PubMed that we manually annotated for those entities and their relationships. 
 First, AAbAAC was used to evaluate several methods on the task of named entity recognition (NER), and second, to fine-tune NER models. 
 Our study demonstrates the utility of AAbAAC for information extraction in the domain of autoimmunity, showing expected improvement in NER performance after fine-tuning. This illustrates the value of small-scale annotation efforts for specialized domains and contributes to the computational study of autoimmunity. The AAbAAC corpus is available at: https://github.com/f-maury/AAbAAC .

AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction

Biomedical named entity recognition (NER) and entity linking (EL) strongly depend on annotated corpora, but the utility of these resources for benchmarking is often assumed rather than characterized. We present a corpus-centric framework for diagnosing benchmark-relevant properties directly from corpus annotations, concept links, train-test splits, document metadata, and terminology mappings. The framework organizes standardized statistics into five families: (1) scale, density and label distribution, (2) lexical and conceptual structure, (3) train-test overlap, (4) metadata composition, and (5) terminology coverage where applicable. Applying the framework to nine corpora spanning diseases, chemicals, and cell types, we find that corpus properties can differ substantially, even when they address the same apparent task. We find differences in the evaluation signal they provide, the generalization demands they impose, the degree of train–test reuse they permit, and the regions of biomedical literature and concept space they represent. These differences suggest that commonly reported corpus statistics can be insufficient to characterize what biomedical NER and EL benchmarks evaluate. We argue that corpus-centric diagnostics provide a practical framework for analyzing corpora beyond surface descriptors such as corpus size and entity type, for identifying potential transfer risks, and for interpreting the scope of benchmarking conclusions. We release the framework as open-source code with an interactive dashboard to support reproducing our analyses and characterizing additional corpora.

What Do Biomedical NER and Entity Linking Benchmarks Measure? A Corpus-Intrinsic Diagnostic Framework

Systematic reviews underpin evidence-based medicine but can outdate quickly when new evidence appears. We formulate a novel prediction task: given a review and new studies that have appeared since its publication, predict whether the review's conclusions will change. A dataset of 3,326 Cochrane review-update pairs is constructed and a range of approaches explored including feature-based baselines, zero and few-shot LLMs, in addition to parameter efficient fine-tuning. Fine-tuning Qwen2.5
 14B achieves the highest AUC-ROC (70.4%).

Can NLP Models Detect When One Publication Outweighs Twenty? Predicting Systematic Review Conclusion Changes

Systematic reviews are fundamental to evidence-based medicine, but the clinical evidence they contain is primarily expressed in unstructured text, making large-scale extraction and reuse difficult. Existing biomedical NLP methods have achieved strong performance on span-level extraction from clinical trials and abstracts; however, these approaches are insufficient for systematic reviews, where evidence is often distributed across multiple studies, sentences, and sections and must be aggregated into normalized document-level attributes. We introduce VaxScope, a benchmark dataset for document-level structured evidence extraction from immunization-related systematic reviews. VaxScope is constructed through an expert-guided semi-automatic annotation pipeline that combines automatic candidate generation with domain expert validation to ensure consistency and annotation quality. We formalize the task as document-level structured extraction, where target labels are defined at the review level and require aggregating evidence beyond isolated textual spans. We further establish baselines for document-level structured extraction using abstract-level input representations and evaluate how access to evidence-grounded contextual input improves performance over abstract-only settings. Baseline experiments show that PubMedBERT achieves the best overall performance (Avg F1: 0.850), with evidence-grounded input improving performance particularly for fields requiring distributed contextual reasoning.

VaxScope: Document-Level Structured Evidence Extraction from Immunization Systematic Reviews

The exponential growth of biomedical literature has made manual curation of biological interaction networks increasingly difficult. Existing automated biological interaction extraction systems address the scaling challenge but treat extraction as a final step, delivering structured output with limited or no integrated support for biologists to interactively verify, correct and contextually interrogate extracted interactions against their source evidence within the same environment. We present Knowledge-Assisted Literature Mining for Biological Interaction Analysis (KALIMBA), an end-to-end, human-in-the-loop platform that integrates three complementary extraction methods (NLP-only, LLM-only, and hybrid) alongside expert annotation and evidence-grounded conversational querying through retrieval-augmented generation (RAG) chat module driven by a dual-context prompt, within a single unified workflow. Evaluation on a corpus of 40 signaling-focused papers demonstrates that the LLM-only back-end recovers substantially more interactions than the NLP-only approach. RAG chat evaluation by a domain expert confirms that the conversational module provides scientifically grounded responses that support curation decisions beyond what the structured interaction table alone conveys.

KALIMBA: Knowledge-Assisted Literature Mining for Biological Interaction Analysis

Medical question answering is a high-stakes setting where factual errors can have serious consequences. Retrieval-augmented generation (RAG) is widely viewed as a promising solution, and prior work has reported substantial gains for large medical QA models. We revisit this assumption across a broad range of open-weight instruction-tuned models spanning 7B to 72B parameters. Across five models, ten biomedical QA datasets, four retrieval methods, and four retrieval corpora, we find that retrieval yields only small and inconsistent improvements over a no-retrieval baseline, typically within 1--2 points. In contrast, the choice of backbone model has a much larger effect than the choice of retriever or corpus, and expert and layman retrieval sources perform similarly in most settings. These results suggest that the main bottleneck is not retrieval quality alone, but the model's limited ability to use retrieved evidence effectively.

Downloads

Next from ACL 2026

Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference

Similar lecture

SYNTHVERIFY: Unleashing the Power of LLMs for Zero-Shot Claim Verification via Step-by-Step Synthetic Data Generation

.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

Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference

Similar lecture

SYNTHVERIFY: Unleashing the Power of LLMs for Zero-Shot Claim Verification via Step-by-Step Synthetic Data Generation

Downloads