Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Benlu, Xia, Iris, Zhang, Yifan, Wang, Junda, Ouyang, Feiyun, Han, Shuo, Cohan, Arman, Yu, Hong, Yao, Zonghai
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Medical thinking with multiple images
by: Yao, Zonghai, et al.
Published: (2026)

ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care
by: Yao, Zonghai, et al.
Published: (2025)

JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability
by: Wang, Junda, et al.
Published: (2024)

PRIME: Planning and Retrieval-Integrated Memory for Enhanced Reasoning
by: Tran, Hieu, et al.
Published: (2025)

MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills
by: Yao, Zonghai, et al.
Published: (2024)

SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
by: Mishra, Prakamya, et al.
Published: (2024)

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
by: Tran, Hieu, et al.
Published: (2024)

ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery
by: Wang, Junda, et al.
Published: (2025)

MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback
by: Yao, Zonghai, et al.
Published: (2024)

Rethinking Patient Education as Multi-turn Multi-modal Interaction
by: Yao, Zonghai, et al.
Published: (2026)

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine
by: Huang, Jiatan, et al.
Published: (2024)

A Novel Method for Calculating Deflection Angle
by: Li, Zonghai
Published: (2024)

A Novel Method for Calculating Deflection Angle with Finite-Distance Correction
by: Li, Zonghai
Published: (2024)

Bayesian Calibration of Win Rate Estimation with LLM Evaluators
by: Gao, Yicheng, et al.
Published: (2024)

On Evaluating LLM Alignment by Evaluating LLMs as Judges
by: Liu, Yixin, et al.
Published: (2025)

References Improve LLM Alignment in Non-Verifiable Domains
by: Shi, Kejian, et al.
Published: (2026)

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
by: Bui, Ngoc, et al.
Published: (2026)

Observable Propagation: Uncovering Feature Vectors in Transformers
by: Dunefsky, Jacob, et al.
Published: (2023)

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
by: Dunefsky, Jacob, et al.
Published: (2025)

Step-level Optimization for Efficient Computer-use Agents
by: Wei, Jinbiao, et al.
Published: (2026)

HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning
by: Han, Simeng, et al.
Published: (2024)

TARSE: Test-Time Adaptation via Retrieval of Skills and Experience for Reasoning Agents
by: Wang, Junda, et al.
Published: (2026)

NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
by: Wang, Junda, et al.
Published: (2023)

Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction
by: Li, Mingchen, et al.
Published: (2026)

From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges
by: Hong, Yihan, et al.
Published: (2026)

MedTutor: A Retrieval-Augmented LLM System for Case-Based Medical Education
by: Jang, Dongsuk, et al.
Published: (2026)

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
by: Wang, Leyao, et al.
Published: (2026)

From Spray to Metric: The Geometric Construction of the Jacobi Metric
by: Li, Zonghai
Published: (2025)

SAGE: Benchmarking and Improving Retrieval for Deep Research Agents
by: Hu, Tiansheng, et al.
Published: (2026)

Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers
by: Zhao, Yilun, et al.
Published: (2025)

EHR Interaction Between Patients and AI: NoteAid EHR Interaction
by: Zhang, Xiaocheng, et al.
Published: (2023)

Exploiting Tree Structure for Credit Assignment in RL Training of LLMs
by: Tran, Hieu, et al.
Published: (2025)

Sam-Guided Enhanced Fine-Grained Encoding with Mixed Semantic Learning for Medical Image Captioning
by: Zhang, Zhenyu, et al.
Published: (2023)

Understanding Reference Policies in Direct Preference Optimization
by: Liu, Yixin, et al.
Published: (2024)

SciDQA: A Deep Reading Comprehension Dataset over Scientific Papers
by: Singh, Shruti, et al.
Published: (2024)

YaleNLP @ PerAnsSumm 2025: Multi-Perspective Integration via Mixture-of-Agents for Enhanced Healthcare QA Summarization
by: Jang, Dongsuk, et al.
Published: (2025)

On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization
by: Flores, Lorenzo Jaime Yu, et al.
Published: (2024)

Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models
by: Riddell, Martin, et al.
Published: (2024)

ResearchGym: Evaluating Language Model Agents on Real-World AI Research
by: Garikaparthi, Aniketh, et al.
Published: (2026)

Improving Summarization with Human Edits
by: Yao, Zonghai, et al.
Published: (2023)