# Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models

arXiv: https://arxiv.org/abs/2608.26587 · HTML: https://mlsanity.com/paper/2608.26587/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 22 of its 47 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 22 of 22)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [Process Reward Models That Think](https://mlsanity.com/paper/2504.16828/) (2025)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [Medical Hallucinations in Foundation Models and Their Impact on Healthcare](https://mlsanity.com/paper/2503.05777/) (2025)
- [Asymmetric Valleys: Beyond Sharp and Flat Local Minima](https://mlsanity.com/paper/1902.00744/) (2019)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot](https://mlsanity.com/paper/2502.04413/) (2025)
- [MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents](https://mlsanity.com/paper/2601.03236/) (2026)
- [Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval](https://mlsanity.com/paper/2410.04585/) (2024)
- [Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models](https://mlsanity.com/paper/2208.08408/) (2022)
- [Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Study](https://mlsanity.com/paper/2308.14321/) (2023)
- [medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs](https://mlsanity.com/paper/2406.14326/) (2024)
- [Overview of the Problem List Summarization (ProbSum) 2023 Shared Task on Summarizing Patients' Active Diagnoses and Problems from Electronic Health Record Progress Notes](https://mlsanity.com/paper/2306.05270/) (2023)
- [Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning](https://mlsanity.com/paper/2503.05193/) (2025)
- [Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning](https://mlsanity.com/paper/2601.15160/) (2026)

## Abstract (arXiv)

Biomedical knowledge graphs (KGs) offer structured medical knowledge that can ground large language model (LLM) reasoning in clinical diagnosis application, yet how KG signal should be integrated into LLMs remains an open question. We present a systematic study spanning five KG task formulations, three training paradigms, two KGs, and three base LLMs. At the task level, all paradigms improve over the non-finetuned baseline, but methods with comparable in-domain accuracy show substantially different knowledge transfer behavior. We introduce Gradient Intervention Density (GID) and Gradient Distortion (GD) to measure how broadly an optimizer modifies the pretrained model. GID and GD together reveal a clear divide: KG-judgment training under KL regularization produces sparse, localized updates (a regime we term as surgical alignment), while task-specific SFT produces dense ones. A controlled ablation shows that the objective and KL contribute to sparsity independently, and the paradigms that produce sparse updates also improve reasoning quality, even when their in-domain accuracy is lower than task-specific SFT. Assessing KG-LLM integration thus requires complementing accuracy with optimization-geometry diagnostics. Our implementation can be found at https://github.com/LARK-NLP-Lab/Surgical-Alignment.