Surprise Alone Learns Lies: Evidence-Gated Continual Learning for LLMs from Streaming Claims

Paper recorded by Signals 4 on 2026-10-29 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-29 on arXiv · recorded by Signals 4 on 2026-10-30

Category: cs.LG · 机器学习 · first seen 2026-10-30

Abstract

Continual learning methods for large language models increasingly decide what to learn by surprise, keeping the inputs the model finds least predictable. This rule is unsafe when the stream contains lies. A planted falsehood about something the model knows has low probability under the model's belief, so it is highly surprising by construction, and a surprise-driven learner absorbs nearly every su

Read on arXiv →