OpenAI 发布 LASER 递归采样方法
Start here
OpenAI introduces the LASER method, selecting samples near the safety policy boundary from synthetic and de-identified conversations to build evaluation sets covering rare scenarios and reduce over-refusals. The authors state that this method requires significantly less annotation compute than random sampling. This efficiency result does not itself imply that models have become safer.
Generated by AI from reports · Updated 6 days ago
Progress timeline
- OpenAI Alignment ResearchSelectedOpenAI releases LASER: recursive sampling to filter safety evaluation dialogues
OpenAI introduces the LASER method, selecting samples near the safety policy boundary from synthetic and de-identified conversations to build evaluation sets covering rare scenarios and reduce over-refusals. The authors state that this method requires significantly less annotation compute than random sampling. This efficiency result does not itself imply that models have become safer.
Related discussion
Attention trend
New sources per day
- Oct 7New1 sources (1 outlets,0 accounts)
- Oct 8New0 sources (0 outlets,0 accounts)
- Oct 9New0 sources (0 outlets,0 accounts)
- Oct 10New0 sources (0 outlets,0 accounts)
- Oct 11New0 sources (0 outlets,0 accounts)
- Oct 12New0 sources (0 outlets,0 accounts)
- Oct 13New0 sources (0 outlets,0 accounts)