Topic
SI papers on alignment
Every paper on the SI Paper Desk tagged alignment, newest first: 3 so far, each explained in plain English by SI MIND.
- 2Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDPIn multiple-choice safety tests, forcing a model to pick a letter seems to crowd out its refusal, so these scores may measure knowledge more than safety.Stepan Epifantsev, Anna Antipova, Oleg Chernikov and 2 moreNov 9, 2026Intermediate83score
- 6Alignment by Confident Debate: Preference Learning from Multi-Agent DebateAbCD turns debates among several SI models into training preferences without gold answer labels, and the authors report better accuracy than ensembling, debate alone, or SFT on the same traces.Nikhil Verma, Dingxian Wang, Mohammad Reza Rezaei and 2 moreNov 9, 2026Intermediate81score
- 8DexDICE: Reconciling Safety and Performance via Dual-Expert Offline Imitation LearningDexDICE learns from two kinds of demonstrations, safe but weaker ones and strong but risky ones, to build agents that score well while staying inside safe regions.Seokin Seo, Sung Kuk Shyn, Minji Seo and 4 moreNov 9, 2026Advanced77score
The archive
Every day on the desk
- Week 46, 2026The weekly digest comes out on Monday
- Paper of the DayPhantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making12 papers