4 citations · 5 across the 7 of their papers we have counts for
6 papers · 1 filter
UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation
Huimin Lu, Masaru Isonuma, Junichiro Mori +1
We present UniDetox, a universally applicable method designed to mitigate toxicity across various large language models (LLMs). Previous detoxification methods are typically model-…
Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation
Huimin Lu, Masaru Isonuma, Junichiro Mori +1
Large language models (LLMs) often inherit biases from vast amounts of training corpora. Traditional debiasing methods, while effective to some extent, do not completely eliminate…
Differentiable Instruction Optimization for Cross-Task Generalization
Masaru Isonuma, Junichiro Mori, Ichiro Sakata
Instruction tuning has been attracting much attention to achieve generalization ability across a wide variety of tasks. Although various types of instructions have been manually cr…
SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation
Tetsu Kasanishi, Masaru Isonuma, Junichiro Mori +1
Automatic literature review generation is one of the most challenging tasks in natural language processing. Although large language models have tackled literature review generation…
Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
Masaru Isonuma, Junichiro Mori, Danushka Bollegala +1
This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian pri…
Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking
Masaru Isonuma, Junichiro Mori, Ichiro Sakata
This paper focuses on the end-to-end abstractive summarization of a single product review without supervision. We assume that a review can be described as a discourse tree, in whic…