IgnitionInnovators at "Discharge Me!": Chain-of-Thought Instruction Finetuning Large Language Models for Discharge Summaries
On the map: LLM reasoning → Clinical and biomedical applications
Abstract (arXiv)
This paper presents our proposed approach to the Discharge Me! shared task, collocated with the 23th Workshop on Biomedical Natural Language Processing (BioNLP). In this work, we develop an LLM-based framework for solving the Discharge Summary Documentation (DSD) task, i.e., generating the two critical target sections `Brief Hospital Course' and `Discharge Instructions' in the discharge summary. By streamlining the recent instruction-finetuning process on LLMs, we explore several prompting strategies for optimally adapting LLMs to specific generation task of DSD. Experimental results show that providing a clear output structure, complimented by a set of comprehensive Chain-of-Thoughts (CoT) questions, effectively improves the model's reasoning capability, and thereby, enhancing the structural correctness and faithfulness of clinical information in the generated text. Source code is available at: https://github.com/antangrocket1312/Discharge_LLM
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 7 of its 29 references that are in the map. First posted on arXiv 24 Jul 2024.
Builds on
7 of 29 references.
References · 7
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 284
- 2022Can language models learn from explanations in context?cited by 248
- 2020Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learningcited by 139
- 2023ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generationcited by 116
- 2022Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Modelscited by 30
Built on by
Citing papers per year: 2024: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Leaps Beyond the Seen: Reinforced Reasoning Augmented Generation for Clinical Notes
- 2024QUB-Cirdan at "Discharge Me!": Zero shot discharge letter generation by open-source LLM
- 2025Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction
- 2022Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine
- 2025DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge
- 2024LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction
- 2025Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs
- 2023Benchmarking large language models for biomedical natural language processing applications and recommendations