Shi

Karma: 85

Praxis Research, George Washington University

https://praxis-research.org/

Mitigating collusive self-preference by redaction and paraphrasing

Taslim, Arush and Shi

2 Apr 2026 8:33 UTC

8 points

0 comments6 min readLW link

Sycophancy Towards Researchers Drives Performative Misalignment

Taywon Min, rustem17, David Vella Zarb and Shi

18 Mar 2026 4:59 UTC

7 points

1 comment21 min readLW link

Self-Recognition Finetuning can Reverse and Prevent Emergent Misalignment

Arush , Shawn Zhou, Jiaxin Wen and Shi

15 Mar 2026 0:11 UTC

51 points

23 comments7 min readLW link

I Am Large, I Contain Multitudes: Persona Transmission via Contextual Inference in LLMs

8 Sep 2025 13:52 UTC

33 points

0 comments1 min readLW link

(www.researchgate.net)

LLM Evaluators Recognize and Favor Their Own Generations

Arjun Panickssery, Sam Bowman and Shi

17 Apr 2024 21:09 UTC

52 points

1 comment3 min readLW link

(tiny.cc)