Papers
arxiv:2610.21477

Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes

Published on Oct 15
Authors:
,
,
,
,
,
,

Abstract

A tool-augmented large language model framework retrieves calculator specifications, synthesizes executable tools, and uses schema-constrained extraction to improve reliable medical calculation from free-form patient notes.

Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to free-form patient notes requires precise variable extraction combined with the exact execution of complex formulas, scoring rules, and output conventions. Relying solely on direct large language model (LLM) prompting is unreliable in this context, as rule recall, parameter extraction, arithmetic reasoning, and formatting become entangled within a single generative step. To address these limitations, we propose a tool-augmented LLM framework for reliable medical calculation from patient notes. The framework retrieves and structures calculator specifications, generates reusable executable tools, and uses a constrained extractor to map each patient note to calculator-ready inputs. The tools then perform deterministic calculation, separating clinical language understanding from rule execution and arithmetic. Evaluated on the MedCalc-Bench dataset, our method achieves 86.73% final-answer accuracy, outperforming the one-shot prompting and supervised fine tuning-only baselines by 24.0 and 17.27 percentage points. Ablation and error analyses show that these performance gains are primarily driven by rule-grounded tool synthesis and schema-constrained extraction, whereas remaining failures are concentrated in clinical-semantic extraction and benchmark-specific output contracts. By grounding calculator logic in executable tools, the proposed approach alleviates arithmetic hallucinations and improves the computational reliability of the final clinical outputs.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2610.21477
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.21477 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.21477 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.