影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
50.21/100
前 8.5%
全站排名 #5,457
发表论文7 篇
平均评分
年均产出2.3 篇/年
Takashi Ishida
研究方向
weakly supervised learning · data evaluation · language model alignment · RLHF · scalable oversight · data contamination
18
Towards Scalable Oversight via Partitioned Human Supervision
ICLR 2026Poster
二作16
How Can I Publish My LLM Benchmark Without Giving the True Answers Away?
ICLR 2026Rejected
一作12
EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements
ICLR 2026Poster
二作16
Practical estimation of the optimal classification error with soft labels and calibration
ICLR 2026Poster
二作21
LLM Routing with Dueling Feedback
ICLR 2026Rejected
二作