Naoto Iwase

岩瀬 直人

Portrait of Naoto Iwase

Naoto Iwase is a medical student at Nagoya University and an incoming visiting student at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). He previously worked as a part-time engineer at Preferred Networks, Inc.

His research focuses on making large language models more reliable and useful in medicine. He develops methods and benchmarks for dependable LLM reasoning, including anytime-valid inference for self-consistency, prefix-consistency checks for chain-of-thought reasoning, and clinical text error correction.

He also writes ML Notes, a collection of survey-style notes on recent machine learning papers.

First-author Works

  1. Reliable Chain-of-Thought via Prefix Consistency

    N. Iwase, Y. Ichihara, M. A. Quamar, J. Komiyama. arXiv:2605.07654, May 2026.

    Correct chain-of-thought traces reproduce their answer under prefix regeneration more often than wrong ones; weighting majority voting by this prefix consistency reaches plateau accuracy at up to 21× fewer tokens (median 4.6×).

    [paper] [project page] [code]

  2. MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts

    N. Iwase, H. Okuyama, J. Iwasawa. arXiv:2511.00421, November 2025.

    A bilingual (Japanese/English) benchmark for medical error correction built from licensing exams; across 9 LLMs, reasoning models substantially outperform standard architectures, and a fine-tuned model exceeds human expert performance.

    [paper] [slides] [code]

See all publications on Google Scholar →

Presentations

Awards