Sahar Abdelnabi
~Sahar_Abdelnabi1
6
论文总数
3.0
年均投稿
平均评分
接收情况3/6
会议分布
ICLR
4
NeurIPS
2
发表论文 (6 篇)
20255 篇
4
The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
NeurIPS 2025Spotlight
4
Filling the Gaps: LLMs for Causal Hypothesis Generation
ICLR 2025Rejected
3
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
ICLR 2025Poster
3
Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
NeurIPS 2025Poster
4
Theory of LLM sampling: part descriptive and part prescriptive
ICLR 2025withdrawn