United States

Clinical documentation is essential for patient care, billing, and medical research, but it is subject to entrenched bias. While manual chart reviews can identify such bias, they are labor-intensive and expert-dependent. We introduce and evaluate StigMAD, a Multi-Agent Debate framework leveraging open-source Large Language Models (LLMs) to detect stigmatizing language in clinical documentation. We investigate reasoning (multi-agent debate), self-reflection, and self-consistency within this framework. Extensive experiments on clinical notes and patient summaries demonstrate that our framework provides significant advantages over rule-based and supervised baselines. A domain-specific LLM (MedGemma) achieved its highest performance using the StigMAD reasoning framework, while a general-purpose LLM (Llama) showed superior results with the self-consistency framework. These findings suggest that open-source LLMs, steered by structured prompting and reflective reasoning, can effectively support the scalable auditing of stigmatizing language, marking a critical step toward more equitable clinical NLP systems.

ACL 2026

Investigating Stigmatizing Language in Clinical Documentation with Open-Source Large Language Models

clinical documentation

stigmatizing language

large language models

## Welcome to 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics!
This year, the conference is in Mexico City. NAACL was actually already planned for Mexico City in 2021, but due to the pandemic the entire conference was moved online. This year, finally, we get to go! So it is my sincere pleasure to welcome you to Mexico City, whether in person or virtually. Having the conference in Mexico City is a good opportunity to emphasize that NAACL is our flagship conference for ACL members not only in North America but also in Central and South America, even though NAACL has been bearing “North” in its name. At this year’s conference, we have a theme to match, with a theme track on the Languages of Latin America to showcase the linguistic diversity of the region.
 
The opportunity to present at NAACL should not depend on a researcher’s travel budget, or their family status. This is why it is so important to make virtual participation at NAACL as good an experience as possible – but we want to also provide a good experience for in-person participants. As a community, we are still working out the best way to do that. This year at NAACL, we are trying out a big virtual poster session ahead of the conference, with the hope that this will make make for a lively and interactive experience. At the same time, we are reducing virtual oral presentations, which seem to be particularly tricky to make to work well. A big thanks to the NAACL program chairs and to Luciana Benotti for all their ideas and work to improve the virtual experience. And participants, virtual as well as in-person: Please let us know what worked for you and what didn’t, so we can continue to improve hybrid conferences. 
 
I have been lucky to work with many amazing people. Without their insight, dedication and patience, and without the many hours of work they put in, NAACL would not have been possible. A huge thank you to the program chairs Helena Gomez, Kevin Duh, and Steve Bethard – you are the best! 
 
Finally, I would like to thank all authors, invited speakers and panelists, area chairs and reviewers, the volunteers organizing and chairing sessions, and all attendees, in-person and virtual. Thank you for helping us make NAACL 2024 come to life. 
 
Welcome and hope you all enjoy the conference! 
Katrin Erk 
The University of Texas at Austin 
NAACL-2024 General Chair 
*You can read the full Welcome message in the [Conference Handbook (downloadable)](https://drive.google.com/file/d/1H1NvW0VASQjkSCYgw3mr-3l4yYDSxz6B/view?usp=sharing)*

To access the event page you need to register [**here.**](http://acl.swoogo.com/naacl2024) 
Your access to the event page is limited based on your registration type. If you registered for workshops only, you will gain access to full workshops content on the day of the workshops program.

Please register!

NAACL 2024

2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

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.

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.

Recent high-complexity agentic systems such as DeepRare perform strongly on rare disease diagnosis benchmarks, but it remains unclear when gains come from structured knowledge access and when they come from parametric
 LLM knowledge. We compare phenotypebased retrieval, LLM reranking, and unrestricted LLM diagnosis across seven benchmarks covering 10,382 cases. We find a clear performance crossover driven by retrieval coverage—the fraction of cases whose true diagnosis is within the retriever's top-50: on highcoverage datasets, ontology-based retrieval dominates; on low-coverage datasets, openended LLM diagnosis takes the lead. Building on this, adding an LLM reranker over retrieved candidates further improves accuracy across our patient-case benchmarks, closing most of the remaining gap to agentic systems (within 2 pp on MME and LIRICAL). We trace the crossover to two structural failure modes
 of ontology-based retrieval—annotation sparsity and phenotypic homogeneity—and show that aggregate scores across mixed benchmarks can hide these qualitatively different diagnostic settings. These findings motivate per-dataset evaluation and hybrid diagnostic systems that combine retrieval, reranking, and parametric LLM generation based on case characteristics.

When Does Retrieval Beat Direct LLM Diagnosis in Rare Disease? An Empirical Study of Ontology Coverage

Extracting structured cancer registry information from pathology and medical reports is challenging due to heterogeneous reporting styles and implicit clinical reasoning. We propose a modular multi-agent framework that decomposes registry abstraction into semantic chunking, retrieval, field-specific extraction, validation, evaluation, and aggregation stages.
 
 The dataset includes 818 annotated cancer cases from Sultan Qaboos University Hospital. Evaluation in this study focuses on breast (n=454) and colorectal (n=174) reports across grade, morphology, TNM staging, and laterality extraction tasks. The framework is compared against prompt-based LLaMA 3.3 baselines using accuracy and weighted/macro F1-score metrics.
 
 The proposed framework improved performance in context-dependent tasks, particularly grade extraction, where weighted F1-score increased from 0.71 to 0.78 for breast cancer and from 0.56 to 0.67 for colorectal cancer. Improvements were also observed for colorectal laterality extraction. For other extraction tasks, particularly highly structured tasks such as TNM staging and morphology extraction, the multi-agent framework achieved performance comparable to direct prompting.
 
 Although the baseline achieved slightly higher average weighted F1-scores overall, the proposed framework provides improved modularity, traceability, and pipeline-level interpretability through explicit intermediate reasoning stages, supporting error analysis and future clinician-guided refinement.

A Multi-Agent Open-Source LLM for Structured Cancer Registry Information Extraction from Pathology and Medical Reports

We investigate how tokenization granularity affects the representation of medical terminology in language models. Prior work links tokenization granularity to downstream performance under contextualized settings for specifically pretrained and fine-tuned models. We instead ask whether this relationship already emerges at the level of isolated term representations across existing pretrained models. We introduce an intrinsic definition retrieval task using UMLS term-definition pairs, with comparison to WordNet. We show that despite substantially heavier fragmentation of medical terminology, the models remain relatively robust in maintaining semantic alignment between medical terms and their definitions. At the same time, tokenization granularity still correlates with retrieval performance, indicating that effects previously observed in downstream biomedical tasks are already reflected at the level of isolated term representations. Encoder models benefit primarily from whole-token preservation, while for decoder LLMs, tokenization effects emerge mainly at deeper retrieval ranks.

Tokenization Granularity and Medical Term Representations in Language Models

Clinical dialogue-to-note generation is challenging because clinically salient evidence is noisy, distributed across turns, and often revised later in the encounter. Direct transcript-only prompting and coarse intermediate scaffolds can therefore suffer from omissions, section leakage, unsupported fill-in, and brittle final-state tracking.
 
 We propose Clinical Atomic Propositions (CAPs), a dialogue-aware intermediate representation for faithful clinical note generation. CAPs extract source-grounded clinical assertions while preserving modifiers such as verification status, temporality, speaker/source, and action type. We also study an optional event consolidation layer that groups CAPs into problem-oriented care bundles before note rendering.
 
 We evaluate five methods on a 197-case ACI-Bench cohort: a transcript-only baseline, prompt-based reimplementations of Cluster2Sent and MEDSUM-ENT, CAP, and CAP+Event. The main task uses a sectioned-note template, with SOAP-template rendering and transcript-free rendering reported as ablations. We use MEDSUM-ENT-style GPT-R/P/F1 metrics and a proposition-grounded semCAP-R/P/F1 audit to measure concept-level and source-grounded faithfulness, complemented by case-level win/tie/loss analysis and clinician deep review.
 
 Results show that CAP improves preservation of transcript-grounded clinical propositions while remaining competitive on concept-level GPT metrics. CAP+Event is not uniformly better than CAP, but qualitative and boundary analyses show when problem-oriented consolidation can improve organization and when compression can introduce omissions. We release code, prompts, intermediate representations, generated notes, and evaluation artifacts at a public repository.

CAP: A Source-Grounded Proposition Scaffold for Faithful Clinical Dialogue-to-Note Generation

Clinical reasoning over electronic health records (EHRs) involves heterogeneous operations, including text interpretation, numerical computation, temporal filtering, and guideline-based aggregation. However, many existing LLM-based approaches still cast these heterogeneous operations as a single end-to-end generation process, obscuring their different reliability requirements and making intermediate failures difficult to inspect. We therefore propose a framework based on operation-mechanism alignment that represents clinical reasoning as a directed acyclic graph of typed operations, where each node is assigned to the execution mechanism best suited to its reliability requirements. The framework also preserves structured evidence provenance for intermediate results. Across six clinician-annotated binary decision tasks, the framework outperforms direct prompting, single-step retrieval-augmented prompting, and chain-of-thought baselines, supporting operation-mechanism alignment as a practical design principle for reliable clinical reasoning over EHRs.

Operation-Mechanism Alignment for Reliable Clinical Reasoning over Electronic Health Records

Despite Spanish being one of the most widely spoken languages in the world, biomedical NLP resources and systematic evaluations remain limited relative to English. We address this gap by constructing and releasing two Spanish biomedical corpora: (1) **MeSHClass-ES**, a 29,063 abstract bilingual corpus translated from PubMed with Opus-MT, and (2) **AnatEM-ES**, the AnatEM anatomical entity corpus translated with a chunk-level LLM-based pipeline that jointly preserves BIO annotations across 13,849 entity mentions. Both corpora achieve a mean COMET score of 0.73 despite using different translation systems. We benchmark nine encoder models spanning general-domain Spanish, domain-specific, and multilingual architectures for both tasks. RigoBERTa-2.0 leads both tasks (micro-F1 classification 0.69, tied with SciBETO-large; NER F1 0.66). Both domain pretraining and model capacity drive performance, with the gap slightly more pronounced for NER (4-point spread) than classification (3-point spread). XLM-RoBERTa-large emerges as a competitive multilingual baseline. A parallel evaluation of four open-weight decoders (7–9B) reveals a task-dependent encoder-decoder gap: QLoRA-adapted Gemma-2-9B reaches 88% of the best encoder on classification (micro-F1 .61 vs .69), but for NER every decoder configuration we tested stays at or below 40% of the best encoder F1. We release both corpora on the HuggingFace Hub1, translation pipelines, and evaluation code on GitHub.

MeSHClass-ES and AnatEM-ES: Open Resources for Spanish Biomedical NLP

When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering

Clinical sources and patient-authored reviews often describe antidepressant side effects in different ways, but these differences are rarely measured directly. We present ClinPeer-AE, a linked dataset for comparing side-effect evidence from PubMed, ClinicalTrials.gov, WebMD, and Drugs.com while preserving source identity. Across five widely prescribed antidepressants, we find low overlap between clinical and peer sources, large differences in relative emphasis, and evidence that many peer-only effects also appear in U.S. Food and Drug Administration Adverse Event Reporting System (FAERS) reports. These findings suggest that patient reviews provide useful context about recurring medication experiences and offer a complementary view of how side effects are described outside formal clinical settings.

From Trials to Reviews: A Cross-Source Dataset for Antidepressant Side Effects

Retrieval-augmented generation (RAG) holds promise for clinical question answering over electronic health records (EHRs), but existing systems treat retrieval as an opaque subroutine, limiting auditability and reliability in patient care workflows. 
 
 We introduce a deterministic multi-stage retrieval pipeline for longitudinal EHR question answering that decomposes retrieval into four distinct, ablated stages where each stage is instrumented with diagnostic metrics, making the flow of clinical evidence measurable and auditable at every step. Evaluated on a broad LLM-annotated cohort and an expert-annotated cardiovascular benchmark developed alongside clinicians from real ICU records, the full pipeline achieves 22-23% relative recall gain over a strong dense retrieval baseline across both cohorts, with consistent improvements in downstream answer quality. 
 
 The pipeline's deterministic and transparent design addresses a critical gap in clinical NLP: retrieval systems that clinicians and researchers can not only rely on, but inspect, audit, and build upon for real-world deployment.

A Deterministic Multi-Stage Retrieval Pipeline for Longitudinal EHR Question Answering

Transformer-based models such as PLM-CA achieve strong performance for automatic ICD coding, but their attention weights do not provide faithful explanations of their predictions. 
 This is a major limitation for electronic medical records, where users often need concise and trustworthy evidence for each assigned code. 
 To address this issue, we jointly train a sentence extractor and an ICD code classifier such that predictions are based only on the extracted sentences. 
 As a result, the extracted sentences serve as faithful rationales for each predicted code and substantially reduce the effort required to inspect long medical records. 
 Experiments on MIMIC-III show that our method approaches the performance of a transformer baseline that processes the full record while using only a small fraction of the document.

Content not yet available

Downloads

Next from ACL 2026

When Does Retrieval Beat Direct LLM Diagnosis in Rare Disease? An Empirical Study of Ontology Coverage

Similar lecture

Testing the Effect of Code Documentation on Large Language Model Code Understanding

Content not yet available

.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

When Does Retrieval Beat Direct LLM Diagnosis in Rare Disease? An Empirical Study of Ontology Coverage

Similar lecture

Testing the Effect of Code Documentation on Large Language Model Code Understanding

Downloads