# Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels

arXiv: https://arxiv.org/abs/2409.16563 · HTML: https://mlsanity.com/paper/2409.16563/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 10 of 10)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://mlsanity.com/paper/2303.04360/) (2023)
- [NegBio: a high-performance tool for negation and uncertainty detection in radiology reports](https://mlsanity.com/paper/1712.05898/) (2017)
- [Exploring the Boundaries of GPT-4 in Radiology](https://mlsanity.com/paper/2310.14573/) (2023)
- [Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels](https://mlsanity.com/paper/2406.17633/) (2024)
- [Closing the gap between open-source and commercial large language models for medical evidence summarization](https://mlsanity.com/paper/2408.00588/) (2024)
- [MedSyn: LLM-based Synthetic Medical Text Generation Framework](https://mlsanity.com/paper/2408.02056/) (2024)
- [CheX-GPT: Harnessing Large Language Models for Enhanced Chest X-ray Report Labeling](https://mlsanity.com/paper/2401.11505/) (2024)
- [Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies](https://mlsanity.com/paper/2402.09282/) (2024)

## Built on by (most cited first, 5 of 5)

- [Effects of Prompt Length on Domain-specific Tasks for Large Language Models](https://mlsanity.com/paper/2502.14255/) (2025)
- [CXR-LT 2024: A MICCAI challenge on long-tailed, multi-label, and zero-shot disease classification from chest X-ray](https://mlsanity.com/paper/2506.07984/) (2025)
- [Effect of Selection Format on LLM Performance](https://mlsanity.com/paper/2503.06926/) (2025)
- [Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports](https://mlsanity.com/paper/2604.19060/) (2026)
- [Med-AR: Autoregressive Vision-Language Pretraining for Long-Tailed Chest X-Ray Classification and Uncertainty-Aware Evaluation](https://mlsanity.com/paper/2609.29156/) (2026)

## Abstract (arXiv)

Despite significant progress in applying large language models (LLMs) to the medical domain, several limitations still prevent them from practical applications. Among these are the constraints on model size and the lack of cohort-specific labeled datasets. In this work, we investigated the potential of improving a lightweight LLM, such as Llama 3.1-8B, through fine-tuning with datasets using synthetic labels. Two tasks are jointly trained by combining their respective instruction datasets. When the quality of the task-specific synthetic labels is relatively high (e.g., generated by GPT4- o), Llama 3.1-8B achieves satisfactory performance on the open-ended disease detection task, with a micro F1 score of 0.91. Conversely, when the quality of the task-relevant synthetic labels is relatively low (e.g., from the MIMIC-CXR dataset), fine-tuned Llama 3.1-8B is able to surpass its noisy teacher labels (micro F1 score of 0.67 v.s. 0.63) when calibrated against curated labels, indicating the strong inherent underlying capability of the model. These findings demonstrate the potential of fine-tuning LLMs with synthetic labels, offering a promising direction for future research on LLM specialization in the medical domain.