Unverified50% confidenceFactExact time
OpenAI explained in a September 2025 paper, "Why Language Models Hallucinate", that most training and benchmarks only score answers as right or wrong and give no credit for "I don't know", which leads models to lean toward guessing.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLarge language models have a miscalibration problem, often answering in a confident tone regardless of whether the answer is correct or incorrect.77% 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% similarVerifiedPerplexity measures a language model's ability to predict test text; the lower the value, the less surprised the model is by the text.74% similarUnverifiedResponses from large language models are typically presented in complete sentences and an affirmative tone, lacking the linguistic signals such as "I'm not sure" or "this needs further verification" that human advisors customarily include.73% similarUnverifiedResearch shows that models trained on low-quality or machine-generated text exhibit significant degradation in linguistic diversity and reasoning accuracy, a phenomenon known as the 'model collapse' effect.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053892API
curl https://kongchang.com/api/v1/knowledge/claims/1053892MCP
get_claim(id=1053892)