mlsanityData to 14 Oct 2026

Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization

arXiv 2407.14000 ↗First posted 19 Jul 2024cs.IR cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Extractive question answering over clinical text is a crucial need to help deal with the deluge of clinical text generated in hospitals. While encoder models (e.g., BERT) have been popular for this reading comprehension task, recently encoder-decoder models (e.g., T5) are on the rise. There is also the emergence of preference optimization techniques to align decoder-only LLMs with human preferences. In this paper, we combine encoder-decoder models with the direct preference optimization (DPO) method to improve over prior state of the art for the RadQA radiology question answering task by 12-15 F1 points. To the best of our knowledge, this effort is the first to show that DPO method also works for reading comprehension via novel heuristics to generate preference data without human inputs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 45 references that are in the map. First posted on arXiv 19 Jul 2024.

Builds on

34 of 45 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  7. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  10. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  11. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  12. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
22 more
  1. 2020Learning to summarize from human feedbackcited by 2,588
  2. 2018Deep contextualized word representationscited by 2,290
  3. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  4. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  5. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 912
  6. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  7. 2022Improving alignment of dialogue agents via targeted human judgementscited by 531
  8. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  9. 2023Statistical Rejection Sampling Improves Preference Optimizationcited by 323
  10. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  11. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 246
  12. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 225
  13. 2015Semi-supervised Sequence Learningcited by 198
  14. 2018The price of debiasing automatic metrics in natural language evaluationcited by 60
  15. 2016Attention-over-Attention Neural Networks for Reading Comprehensioncited by 31
  16. 2019Sample Efficient Text Summarization Using a Single Pre-Trained Transformercited by 27
  17. 2016ReasoNet: Learning to Stop Reading in Machine Comprehensioncited by 21
  18. 2019Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehensioncited by 15
  19. 2022Human-in-the-loop Abstractive Dialogue Summarizationcited by 8
  20. 2017Referenceless Quality Estimation for Natural Language Generationcited by 4
  21. 2020MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehensioncited by 3
  22. 2023RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithmcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-step retrieval and reasoning improves radiology question answering with large language models
  2. 2026Yale-DM-Lab at ArchEHR-QA 2026: Deterministic Grounding and Multi-Pass Evidence Alignment for EHR Question Answering
  3. 2025Adapting Lightweight Vision Language Models for Radiological Visual Question Answering
  4. 2025RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval
  5. 2025ReXVQA: A Large-scale Visual Question Answering Benchmark for Generalist Chest X-ray Understanding
  6. 2026Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA
  7. 2026Domain Fine-Tuning vs. Retrieval-Augmented Generation for Medical Multiple-Choice Question Answering: A Controlled Comparison at the 4B-Parameter Scale
  8. 2026Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs