Ansh Radhakrishnan

Ansh Radhakrishnan on Hugging Face Daily Papers: 3 papers, 1 in the top 3 of their day, 74 upvotes.

1. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training 30 upvotes, #5 of 2024-01-12
2. Measuring Faithfulness in Chain-of-Thought Reasoning 29 upvotes, #2 of 2023-07-27
3. Question Decomposition Improves the Faithfulness of Model-Generated Reasoning 15 upvotes, #5 of 2023-07-25

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.