belief-updating

Tag

Cards List
#belief-updating

@QuixiAI: Announcing QuixiAI/SYN-1B - A synthetic pretraining dataset designed to teach models to track rules, update beliefs aft…

X AI KOLs Timeline · 2026-07-06

QuixiAI releases SYN-1B, a synthetic pretraining dataset designed to teach models rule tracking, belief updating, and evidence preservation over long contexts, available on Hugging Face.

0 favorites 0 likes
#belief-updating

Evidence-Informed LLM Beliefs for Continual Scientific Discovery

arXiv cs.AI · 2026-06-30 Cached

This paper addresses the limitation of static surprisal in LLM-based scientific discovery by introducing evidence-informed non-stationary beliefs, and proposes belief-update filtering and diversity maximization to improve discovery, achieving 30.62% higher non-stationary surprisal across five domains.

0 favorites 0 likes
← Back to home

Submit Feedback