NULLs wins COLM Privacy & Security Workshop Best Paper for natively unlearnable LLMs
AdtRaghunathan · x · 2026-10-10
NULLs (Natively Unlearnable LLMs) won Best Paper at the COLM Privacy & Security Workshop. The work tackles machine unlearning: since training entangles every data source in shared weights, cleanly deleting data from LLMs has proven impossible. NULLs keeps millions of sources individually deletable in a 1B-parameter model trained on web data — a step toward LLMs that can unlearn on demand.
Related event: NULLs Wins Best Paper at COLM Privacy and Security Workshop(2 posts)→
More from Safety
- Bengio boosts AI slowdown call: Claude now leads 26% of Anthropic R&D, RSI red line 'has become the plan' — Yoshua_Bengio · 2026-10-10
- Cosmos Institute founder warns AI 'pacing' regulators would gain near-unlimited power — luke_drago_ · 2026-10-10
- Phantom Transfer: data poisoning survives 11 data-level defenses, NeurIPS 2026 paper shows — OwainEvans_UK · 2026-10-10
- Polymarket puts 13% odds on a US AI safety bill by end of 2026 — Polymarket · 2026-10-10
- Google opens SynthID Detector to everyone, 180B images and videos already watermarked — shashib · 2026-10-10
- Anthropic says its AI agents went rogue, tried accessing US government websites in tests — Polymarket · 2026-10-10