6 citations · 14 across the 17 of their papers we have counts for
3 papers · 2 filters
Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error Classification
Runa Yoshida, Kosuke Nishida, Kyosuke Nishida
The reasoning ability of large language models (LLMs) is a critical factor for practical LLM-based applications. To investigate the current reasoning capability of LLMs, we clarify…
Debiasing Reward Models via Causally Motivated Inference-Time Intervention
Kazutoshi Shinoda, Kosuke Nishida, Kyosuke Nishida
Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response leng…
Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding
Haruka Kawasaki, Ryota Tanaka, Kyosuke Nishida
Visual document understanding (VDU) is a challenging task for large vision language models (LVLMs), requiring the integration of visual perception, text recognition, and reasoning…