Unverified50% confidenceFactExact time
Language models generally suffer from overconfidence, especially in CoT, where erroneous steps are often written in as fluent and as confident a tone as correct steps, making them hard for readers to distinguish.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedEarly large language models suffered from serious overconfidence, tending to give definitive statements even for uncertain answers, which is the hallucination phenomenon.80% similarVerifiedCurrent mainstream large language models are generally overconfident, partly because the training objective optimizes for the fluency of predicting the next word rather than the actual reliability of the output.75% similarVerifiedText generated by large language models tends to have low perplexity, with word choices that are overly consistent with probabilistic expectations, lacking the unexpectedness of human writing.75% similarUnverifiedLanguage model outputs are probabilistic and semantically ambiguous, making it difficult to measure quality with precise assertions, which poses challenges for migrating TDD concepts to the prompt engineering domain.72% similarVerifiedCurrent large language models lack reliable self-introspection capabilities.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084636API
curl https://kongchang.com/api/v1/knowledge/claims/1084636MCP
get_claim(id=1084636)