Decision-only training teaches shortcuts that skip belief formation
JessicaHullman · x · 2026-10-23
Thread follow-up: decision-only training substantially reduces total regret with minimal belief improvement, suggesting models learn shortcuts that skip belief formation; forcing the LLM to state beliefs first makes most of the gain disappear. Charts across synthetic, weather, and clinical domains support the finding.
More from Research
- MPI-Sec PhD Thesis on Vulnerability Detection Benchmarks Includes Pre-LLM Classic "Top Score on the Wrong Exam" — mboehme_ · 2026-10-23
- New paper makes 9 falsifiable predictions toward a major AI-enabled terror attack by 2027-2028 — StephenLCasper · 2026-10-23
- HumanoidPose recovers humanoid robots' full-body joint states from RGB video alone — cholz · 2026-10-23
- Sophont's Holon-S1 predicts genes and biomarkers from routine pathology slides — iScienceLuvr · 2026-10-23
- Glasgow study: raised eyebrows and slow blinks make speakers look confident — Limor_Raviv · 2026-10-23
- IFM open-sources RL360, the agentic RL infra behind K2 Horizon's training — rupspace · 2026-10-23