UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting

• URL: http://arxiv.org/abs/2506.05589v1
• Date: Thu, 05 Jun 2025 21:07:55 GMT
• Title: UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting
• Abstract summary: We describe our system for answering clinical questions using electronic health records.<n>Our approach uses large language models in two steps: first, to find sentences relevant to a clinician's question, and second, to generate a short, citation-supported response.
• Score: 5.882312167168893
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps: first, to find sentences in the EHR relevant to a clinician's question, and second, to generate a short, citation-supported response based on those sentences. We use few-shot prompting, self-consistency, and thresholding to improve the sentence classification step to decide which sentences are essential. We compare several models and find that a smaller 8B model performs better than a larger 70B model for identifying relevant information. Our results show that accurate sentence selection is critical for generating high-quality responses and that self-consistency with thresholding helps make these decisions more reliable.

Related papers

• Boosting Self-Consistency with Ranking [56.38798757709555]
  Self-consistency improves large language models by sampling multiple reasoning paths and selecting the most frequent answer.<n>We address this limitation with Ranking-Improved Self-Consistency (RISC), which reformulates answer selection in self-consistency as a ranking problem.
  arXiv  Detail & Related papers  (2026-06-03T16:12:30Z)
• HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering [4.835744579415159]
  This paper presents the system developed by the HealthNLP_Retrievers team for this task.<n>The proposed approach uses a multi-stage cascaded pipeline powered by the Gemini 2.5 Pro large language model.<n>Our architecture comprises four integrated modules: (1) a few-shot query reformulation unit which summarizes patient queries; (2) a verbose-based evidence scorer which ranks clinical sentences to recall; and (3) a grounded response generator which synthesizes professional-caliber answers.
  arXiv  Detail & Related papers  (2026-04-29T16:47:20Z)
• Benchmarking Uncertainty Calibration in Large Language Model Long-Form Question Answering [7.1559850008795385]
  Large Language Models (LLMs) are commonly used in Question Answering (QA) settings.<n>Existing UQ approaches remain weakly validated in scientific QA.<n>We introduce the first large-scale benchmark for evaluating UQ metrics in reasoning-demanding QA.
  arXiv  Detail & Related papers  (2026-01-30T20:02:34Z)
• EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records [31.559633376006442]
  EHRNavigator is a multi-agent framework that harnesses AI agents to perform patient-level question answering across heterogeneous and multimodal EHR data.<n>It achieved 86% accuracy on real-world cases while maintaining clinically acceptable response times.
  arXiv  Detail & Related papers  (2026-01-15T03:02:15Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs [7.692452997544737]
  Large language models (LLMs) offer a promising solution for extracting and reasoning over unstructured text.<n>Retrieval-augmented generation (RAG) offers an alternative by retrieving task-relevant passages from across the entire EHR.<n>Our results suggest that RAG remains a competitive and efficient approach even as newer models become capable of handling increasingly longer amounts of text.
  arXiv  Detail & Related papers  (2025-08-20T16:09:37Z)
• Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering [3.3260862557368926]
  We present Neural, the runner-up in the BioNLP 2025 Arch-QA shared task on evidence-grounded clinical QA.<n>Our proposed method decouples the task into (1) sentence-level evidence identification and (2) answer synthesis with explicit citations.<n>A self-consistency voting scheme further improves evidence recall without sacrificing precision.
  arXiv  Detail & Related papers  (2025-06-12T14:36:18Z)
• A Dataset for Addressing Patient's Information Needs related to Clinical Course of Hospitalization [15.837772594006038]
  ArchEHR-QA is an expert-annotated dataset based on real-world patient cases from intensive care unit and emergency department settings.<n>Cases comprise questions posed by patients to public health forums, clinician-interpreted counterparts, relevant clinical note excerpts with sentence-level relevance annotations, and clinician-authored answers.<n>The answer-first prompting approach consistently performed best, with Llama 4 achieving the highest scores.
  arXiv  Detail & Related papers  (2025-06-04T16:55:08Z)
• Give me Some Hard Questions: Synthetic Data Generation for Clinical QA [13.436187152293515]
  This paper explores generating Clinical QA data using large language models (LLMs) in a zero-shot setting.<n>We find that naive prompting often results in easy questions that do not reflect the complexity of clinical scenarios.<n>Experiments on two Clinical QA datasets demonstrate that our method generates more challenging questions, significantly improving fine-tuning performance over baselines.
  arXiv  Detail & Related papers  (2024-12-05T19:35:41Z)
• Aligning Large Language Models by On-Policy Self-Judgment [49.31895979525054]
  Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. We present a novel alignment framework, SELF-JUDGE, that does on-policy learning and is parameter efficient. We show that the rejecting sampling by itself can improve performance further without an additional evaluator.
  arXiv  Detail & Related papers  (2024-02-17T11:25:26Z)
• PEDANTS: Cheap but Effective and Interpretable Answer Equivalence [10.367359022491181]
  We provide rubrics and datasets for evaluating machine QA adopted from the Trivia community. We also propose an efficient, and interpretable QA evaluation that is more stable than an exact match and neural methods(BERTScore)
  arXiv  Detail & Related papers  (2024-02-17T01:56:19Z)
• MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering [64.6741991162092]
  We present MinPrompt, a minimal data augmentation framework for open-domain question answering. We transform the raw text into a graph structure to build connections between different factual sentences. We then apply graph algorithms to identify the minimal set of sentences needed to cover the most information in the raw text. We generate QA pairs based on the identified sentence subset and train the model on the selected sentences to obtain the final model.
  arXiv  Detail & Related papers  (2023-10-08T04:44:36Z)
• SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References [73.67707138779245]
  We propose a new evaluation metric: SQuArE (Sentence-level QUestion AnsweRing Evaluation) We evaluate SQuArE on both sentence-level extractive (Answer Selection) and generative (GenQA) QA systems.
  arXiv  Detail & Related papers  (2023-09-21T16:51:30Z)
• Double Retrieval and Ranking for Accurate Question Answering [120.69820139008138]
  We show that an answer verification step introduced in Transformer-based answer selection models can significantly improve the state of the art in Question Answering. The results on three well-known datasets for AS2 show consistent and significant improvement of the state of the art.
  arXiv  Detail & Related papers  (2022-01-16T06:20:07Z)
• MS-Ranker: Accumulating Evidence from Potentially Correct Candidates for Answer Selection [59.95429407899612]
  We propose a novel reinforcement learning based multi-step ranking model, named MS-Ranker. We explicitly consider the potential correctness of candidates and update the evidence with a gating mechanism. Our model significantly outperforms existing methods that do not rely on external resources.
  arXiv  Detail & Related papers  (2020-10-10T10:36:58Z)
• Harvesting and Refining Question-Answer Pairs for Unsupervised QA [95.9105154311491]
  We introduce two approaches to improve unsupervised Question Answering (QA) First, we harvest lexically and syntactically divergent questions from Wikipedia to automatically construct a corpus of question-answer pairs (named as RefQA) Second, we take advantage of the QA model to extract more appropriate answers, which iteratively refines data over RefQA.
  arXiv  Detail & Related papers  (2020-05-06T15:56:06Z)
• A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection [112.0514737686492]
  In this paper, we argue that by exploiting the intrinsic structure of the original rank together with an effective word-relatedness encoder, we can achieve competitive results. Our model takes 9.5 seconds to train on the WikiQA dataset, i.e., very fast in comparison with the $sim 18$ minutes required by a standard BERT-base fine-tuning.
  arXiv  Detail & Related papers  (2020-03-04T22:12:18Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.