Saved in:
Bibliographic Details
Main Authors: Shao, Jiahao, Khan, Anam Nawaz, Brett, Christopher, Berg, Tom, Li, Xueping, Yao, Bing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.13328
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910130135629824
author Shao, Jiahao
Khan, Anam Nawaz
Brett, Christopher
Berg, Tom
Li, Xueping
Yao, Bing
author_facet Shao, Jiahao
Khan, Anam Nawaz
Brett, Christopher
Berg, Tom
Li, Xueping
Yao, Bing
contents Pathology reports serve as the definitive record for breast cancer staging, yet their unstructured format impedes large-scale data curation. While Large Language Models (LLMs) offer semantic reasoning, their deployment is often limited by high computational costs and hallucination risks. This study introduces a parameter-efficient, multi-task framework for automating the extraction of Tumor-Node-Metastasis (TNM) staging, histologic grade, and biomarkers. We fine-tune a Llama-3-8B-Instruct encoder using Low-Rank Adaptation (LoRA) on a curated, expert-verified dataset of 10,677 reports. Unlike generative approaches, our architecture utilizes parallel classification heads to enforce consistent schema adherence. Experimental results demonstrate that the model achieves a Macro F1 score of 0.976, successfully resolving complex contextual ambiguities and heterogeneous reporting formats that challenge traditional extraction methods including rule-based natural language processing (NLP) pipelines, zero-shot LLMs, and single-task LLM baselines. The proposed adapter-efficient, multi-task architecture enables reliable, scalable pathology-derived cancer staging and biomarker profiling, with the potential to enhance clinical decision support and accelerate data-driven oncology research.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13328
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Task LLM with LoRA Fine-Tuning for Automated Cancer Staging and Biomarker Extraction
Shao, Jiahao
Khan, Anam Nawaz
Brett, Christopher
Berg, Tom
Li, Xueping
Yao, Bing
Machine Learning
Pathology reports serve as the definitive record for breast cancer staging, yet their unstructured format impedes large-scale data curation. While Large Language Models (LLMs) offer semantic reasoning, their deployment is often limited by high computational costs and hallucination risks. This study introduces a parameter-efficient, multi-task framework for automating the extraction of Tumor-Node-Metastasis (TNM) staging, histologic grade, and biomarkers. We fine-tune a Llama-3-8B-Instruct encoder using Low-Rank Adaptation (LoRA) on a curated, expert-verified dataset of 10,677 reports. Unlike generative approaches, our architecture utilizes parallel classification heads to enforce consistent schema adherence. Experimental results demonstrate that the model achieves a Macro F1 score of 0.976, successfully resolving complex contextual ambiguities and heterogeneous reporting formats that challenge traditional extraction methods including rule-based natural language processing (NLP) pipelines, zero-shot LLMs, and single-task LLM baselines. The proposed adapter-efficient, multi-task architecture enables reliable, scalable pathology-derived cancer staging and biomarker profiling, with the potential to enhance clinical decision support and accelerate data-driven oncology research.
title Multi-Task LLM with LoRA Fine-Tuning for Automated Cancer Staging and Biomarker Extraction
topic Machine Learning
url https://arxiv.org/abs/2604.13328