scalable-oversight

Tag

Cards List
#scalable-oversight

Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

arXiv cs.AI · 2026-06-02 Cached

Proposes on-policy critique distillation (Opcd) using weak models as critics to provide revision directions for strong models, improving reasoning and alignment without requiring weak models to solve tasks.

0 favorites 0 likes
#scalable-oversight

AI-written critiques help humans notice flaws

OpenAI Blog · 2022-06-13 Cached

OpenAI trained language models to write critiques of text summaries, helping human evaluators spot flaws more effectively — a step toward scalable oversight of AI systems on difficult tasks. The work explores how AI-assisted feedback can improve human evaluation quality as a proof of concept for alignment research.

0 favorites 0 likes
#scalable-oversight

Summarizing books with human feedback

OpenAI Blog · 2021-09-23 Cached

OpenAI presents a scalable alignment technique using hierarchical summarization of entire books with human feedback, demonstrating how models can be trained to act in accordance with human intentions on complex, difficult-to-evaluate tasks.

0 favorites 0 likes
#scalable-oversight

Apr 14, 2026AlignmentAutomated Alignment Researchers: Using large language models to scale scalable oversight

Anthropic Research · 2026-05-08 Cached

Anthropic researchers demonstrate that Claude Opus 4.6 can autonomously act as an alignment researcher to improve weak-to-strong supervision techniques, addressing challenges in scalable oversight.

0 favorites 0 likes
← Back to home

Submit Feedback