Yoichi Ishibashi

Yoichi Ishibashi is a Researcher at NEC.

My research interest lies in LLMs, Coding Agents, and Self-Evolving LLMs.

For more details, please refer to my CV.

news

May 22, 2025	Our paper Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning has been published on arXiv.
Feb 13, 2025	Our paper Can Large Language Models Invent Algorithms to Improve Themselves? has been accepted to NAACL 2025🎉
Oct 22, 2024	Our paper Can Large Language Models Invent Algorithms to Improve Themselves? has been published on arXiv.
Mar 14, 2024	Our paper Subspace Representations for Soft Set Operations and Sentence Similarities has been accepted to NAACL 2024🎉
Oct 07, 2023	Our paper, titled Knowledge Sanitization of Large Language Models, has been published on arXiv.

selected publications

Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning

Yoichi Ishibashi, Taro Yano, and Masafumi Oyamada

arXiv, 2025

PDF
Can Large Language Models Invent Algorithms to Improve Themselves?

Yoichi Ishibashi, Taro Yano, and Masafumi Oyamada

NAACL, 2025

PDF
Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization

Yoichi Ishibashi and Nishimura Yoshimasa

arXiv, 2024

PDF Code
Knowledge Sanitization of Large Language Models

Yoichi Ishibashi and Hidetoshi Shimodaira

arXiv, 2023

DOI PDF Code
Evaluating the Robustness of Discrete Prompts

Yoichi Ishibashi, Danushka Bollegala, Katsuhito Sudoh, and 1 more author

EACL, 2023

Abs PDF

Discrete prompts have been used for fine-tuning Pre-trained Language Models for diverse NLP tasks. In particular, automatic methods that generate discrete prompts from a small set of training instances have reported superior performance. However, a closer look at the learnt prompts reveals that they contain noisy and counter-intuitive lexical constructs that would not be encountered in manually-written prompts. This raises an important yet understudied question regarding the robustness of automatically learnt discrete prompts when used in downstream tasks. To address this question, we conduct a systematic study of the robustness of discrete prompts by applying carefully designed perturbations into an application using AutoPrompt and then measure their performance in two Natural Language Inference (NLI) datasets. Our experimental results show that although the discrete prompt-based method remains relatively robust against perturbations to NLI inputs, they are highly sensitive to other types of perturbations such as shuffling and deletion of prompt tokens. Moreover, they generalize poorly across different NLI datasets. We hope our findings will inspire future work on robust discrete prompt learning.