Search Results for author: Masaru Isonuma

Found 7 papers, 3 papers with code

Unlearning Reveals the Influential Training Data of Language Models

no code implementations26 Jan 2024 Masaru Isonuma, Ivan Titov

This paper presents UnTrac, which estimates the influence of a training dataset by unlearning it from the trained model.

Differentiable Instruction Optimization for Cross-Task Generalization

no code implementations16 Jun 2023 Masaru Isonuma, Junichiro Mori, Ichiro Sakata

Instruction tuning has been attracting much attention to achieve generalization ability across a wide variety of tasks.

Bilevel Optimization

SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation

1 code implementation24 May 2023 Tetsu Kasanishi, Masaru Isonuma, Junichiro Mori, Ichiro Sakata

Automatic literature review generation is one of the most challenging tasks in natural language processing.

Review Generation

Tree-Structured Neural Topic Model

no code implementations ACL 2020 Masaru Isonuma, Junichiro Mori, Danushka Bollegala, Ichiro Sakata

This paper presents a tree-structured neural topic model, which has a topic distribution over a tree with an infinite number of branches.

Cannot find the paper you are looking for? You can Submit a new open access paper.