Author

Kiyoaki Shirai

h-index 2 View on Semantic Scholar

We have 2 of 23 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Attention-Guided Layer Selection for Contrastive Decoding in Large Language Models

Three attention-guided strategies are proposed: Attention-JSD, Attention-Entropy-Max, and Attention-Entropy-Min, which leverage structural information carried by internal self-attention mechanisms as a signal for layer selection and observe significant gains on multi-answer metrics.

Yusuke Sakai, Natthawut Kertkeidkachorn, Kiyoaki Shirai · arXiv.org · 0 citations

Preprint Aug 2026

Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation

Results demonstrate that the proposed method outperforms the baselines, including an LLM without debiasing and previous calibration methods, and it is confirmed that scoring bias varies across LLMs, tasks, and score ranges, indicating the importance of measuring latent number bias as the case may be.

Yuma Asato, Kiyoaki Shirai, Natthawut Kertkeidkachorn · 0 citations