Yoichi Ishibashi

Yoichi Ishibashi is a Researcher at NEC.

My research interests include Natural Language Processing (NLP), Large Language Models (LLMs), Prompt Learning, and LLM Agent.

For more details, please refer to my CV.

news

Mar 14, 2024	Our paper Subspace Representations for Soft Set Operations and Sentence Similarities has been accepted to NAACL 2024🎉
Oct 7, 2023	Our paper, titled Knowledge Sanitization of Large Language Models, has been published on arXiv.
Sep 19, 2023	A column on our recent paper on prompt learning has been published at Journal of Natural Language Processing.
May 7, 2023	Our paper Evaluating the Robustness of Discrete Prompts has been accepted to EACL 2023 🎉
Apr 1, 2023	I have joined Kyoto University as a postdoctoral researcher.

selected publications

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

Yoichi Ishibashi, and Yoshimasa Nishimura

arXiv, 2024

PDF Code
Knowledge Sanitization of Large Language Models

Yoichi Ishibashi, and Hidetoshi Shimodaira

arXiv, 2023

PDF Code
Evaluating the Robustness of Discrete Prompts

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

In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, May 2023

Abs PDF Code

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.