Francis Rhys Ward

~Francis_Rhys_Ward1

6

论文总数

3.0

年均投稿

5.4

平均评分

接收情况3/6

会议分布

NeurIPS

3

ICLR

2

ICML

1

发表论文 (6 篇)

20253 篇

CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D

NeurIPS 2025Spotlight

AI Sandbagging: Language Models can Strategically Underperform on Evaluations

ICLR 2025Poster

The Elicitation Game: Evaluating Capability Elicitation Techniques

ICML 2025Poster

20243 篇

Tall Tales at Different Scales: Evaluating Scaling Trends For Deception in Language Models

ICLR 2024Rejected

A Causal Model of Theory-of-Mind in AI Agents

NeurIPS 2024Rejected

AI Sandbagging: Language Models can Strategically Underperform on Evaluations

NeurIPS 2024Rejected

合作者 (20)

Felix Hofstätter4 篇

Teun van der Weij4 篇

Oliver Jaffe3 篇

Samuel F. Brown3 篇

Jack Foxabbott1 篇

Rohan Subramani1 篇

Henning Bartsch1 篇