Ruizhe Li

Ruizhe Li on Hugging Face Daily Papers: 4 papers, 0 in the top 3 of their day, 28 upvotes.

1. When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs 6 upvotes, #74 of 2026-10-02
2. See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs 4 upvotes, #60 of 2026-10-01
3. Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space 10 upvotes, #30 of 2026-09-04
4. Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs 7 upvotes, #8 of 2026-01-20

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.