mlsanityData to 14 Oct 2026

heiDS at ArchEHR-QA 2025: From Fixed-k to Query-dependent-k for Retrieval Augmented Generation

arXiv 2506.19512 ↗First posted 24 Jun 2025cs.CLcited by 0

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

This paper presents the approach of our team called heiDS for the ArchEHR-QA 2025 shared task. A pipeline using a retrieval augmented generation (RAG) framework is designed to generate answers that are attributed to clinical evidence from the electronic health records (EHRs) of patients in response to patient-specific questions. We explored various components of a RAG framework, focusing on ranked list truncation (RLT) retrieval strategies and attribution approaches. Instead of using a fixed top-k RLT retrieval strategy, we employ a query-dependent-k retrieval strategy, including the existing surprise and autocut methods and two new methods proposed in this work, autocut* and elbow. The experimental results show the benefits of our strategy in producing factual and relevant answers when compared to a fixed-k.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 32 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

17 of 32 references.

References · 17

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2017Billion-scale similarity search with GPUscited by 2,497
  3. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  4. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  5. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 288
  6. 2023ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generationcited by 118
  7. 2023Do Language Models Know When They're Hallucinating References?cited by 116
  8. 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 100
  9. 2024ContextCite: Attributing Model Generation to Contextcited by 98
  10. 2023A Survey of Large Language Models Attributioncited by 71
  11. 2024Training Language Models to Generate Text with Citations via Fine-grained Rewardscited by 42
  12. 2024EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summariescited by 35
5 more
  1. 2024Ranked List Truncation for Large Language Model-based Re-Rankingcited by 20
  2. 2025A Dataset for Addressing Patient's Information Needs related to Clinical Course of Hospitalizationcited by 13
  3. 2024Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decompositioncited by 12
  4. 2024Systematic Task Exploration with LLMs: A Study in Citation Text Generationcited by 8
  5. 2025MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letterscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA
  2. 2024Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health records
  3. 2024Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering
  4. 2025Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented Generation
  5. 2026When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
  6. 2026RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering
  7. 2026CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain
  8. 2026A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering