Weikai Li

~Weikai_Li2

3

论文总数

1.5

年均投稿

6.3

平均评分

接收情况2/3

会议分布

ICLR

2

COLM

1

发表论文 (3 篇)

20251 篇

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence

COLM 2025Poster

20242 篇

When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks

ICLR 2024Rejected

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

ICLR 2024Poster

合作者 (20)

Jianhui Chen2 篇

Kaisheng Zeng2 篇

Xiaozhi Wang2 篇