Search arXiv⌕ Search

arXiv · 2509.16584

From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations

Abstract

Large language models (LLMs) have demonstrated promising performance on medical benchmarks; however, their ability to perform medical calculations, a crucial aspect of clinical decision-making, remains underexplored and poorly evaluated. Existing benchmarks often assess only the final answer with a wide numerical tolerance, overlooking systematic reasoning failures and potentially causing serious clinical misjudgments. In this work, we revisit medical calculation evaluation with a stronger focus on clinical trustworthiness. First, we clean and restructure the MedCalc-Bench dataset and propose a new step-by-step evaluation pipeline that independently assesses formula selection, entity extraction, and arithmetic computation. Under this granular framework, the accuracy of GPT-4o drops from 62.7% to 43.6%, revealing errors masked by prior evaluations. Second, we introduce an automatic error analysis framework that generates structured attribution for each failure mode. Human evaluation confirms its alignment with expert judgment, enabling scalable and explainable diagnostics. Finally, we propose a modular agentic pipeline, MedRaC, that combines retrieval-augmented generation and Python-based code execution. Without any fine-tuning, MedRaC improves the accuracy of different LLMs from 16.35% up to 53.19%. Our work highlights the limitations of current benchmark practices and proposes a more clinically faithful methodology. By enabling transparent and transferable reasoning evaluation, we move closer to making LLM-based systems trustworthy for real-world medical applications.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Benlu Wang, Iris Xia, Yifan Zhang, Junda Wang, Feiyun Ouyang, Shuo Han, Arman Cohan, Hong Yu, Zonghai Yao. 2026-01-31. From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations. https://arxiv.org/abs/2509.16584

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

MultiViewDx: Evidence-Linked Multi-View Clinical Diagnosis

Medical multimodal large language models (MLLMs) can perform well on existing medical visual question answering (MedVQA) benchmarks, but their training data often does not match clinical diagnosis. Most supervision is organized around isolated images or short QA pairs, leaving two structures weakly specified: how evidence leads to a decision, and how views, series, modalities, and patient context from the same case are linked. We introduce MultiViewDx, a partly physician-validated multimodal instruction dataset for evidence-linked multi-view medical imaging diagnosis. MultiViewDx uses the clinical case as the supervision unit. It links imaging studies with patient context, normalizes heterogeneous reports into an evidence-linked workflow (evidence -> findings -> differential discussion -> diagnosis), and uses a unified image-text retriever to constrain instruction synthesis to source-supported evidence. It covers X-ray, CT, MRI, ultrasound, histopathology, and other clinical visual sources. We fine-tune MultiViewDx-8B-AN and evaluate it on both existing MedVQA benchmarks and real-world case-based diagnostic reasoning. Across four MedVQA benchmarks, it achieves the best average accuracy among compared systems (79.0%), outperforming HuatuoGPT-Vision-34B (66.7%) and Claude3-Opus (55.7%). Beyond MedVQA, on JAMA Clinical Challenge cases, it receives the strongest overall rating under a physician-designed rubric for key clinical points, diagnostic inference, and evidence grounding. Controlled ablations and clinician evaluation show that both case-level multi-view organization and evidence-linked reasoning targets contribute to the gain.

cs.CL↗

Foundations of Large Language Models

This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all cutting-edge technologies. The book is structured into six main chapters, each exploring a key area: pre-training, generative models, prompting, alignment, inference, and reasoning. It is intended for college students, professionals, and practitioners in natural language processing and related fields, and can serve as a reference for anyone interested in large language models.

cs.CL↗

Interactive In-Meeting Speaker Correction with Human Feedback

Most automatic speech processing systems operate in ``open loop'' mode without user feedback about who said what, yet human-in-the-loop workflows can potentially enable higher accuracy. We propose an LLM-assisted in-meeting speaker correction system that lets users fix speaker attribution errors through brief corrective feedback. After performing streaming ASR and diarization, the system presents concise LLM-generated summaries to help users identify important speaker errors, and it incorporates user feedback by updating the speaker-attributed transcript and adding online speaker enrollments. To make this workflow effective despite errors in speech processing, LLM analysis, and user feedback, we developed several mechanisms to identify the intended correction more precisely. Further, we built an LLM-driven user feedback simulation to evaluate the workflow reprodubilty and at scale. Applied to the AMI headset test set, our system substantially reduces the DER from a streaming baseline (Google ASR + ECAPA) by 31.99% and speaker substitution error by 52.68%. Results of a pilot usability study suggest several avenues to improve the user experience.

cs.CL↗