Defines mistake-bounded generation and gives an algorithm for finite classes achieving optimal last-mistake time Cdim(L) with floor(log2 |L|) mistakes, plus a trade-off for infinite classes and noisy extensions.
Proceedings of the 57th Annual ACM Symposium on Theory of Computing , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
citing papers explorer
-
Mistake-Bounded Language Generation
Defines mistake-bounded generation and gives an algorithm for finite classes achieving optimal last-mistake time Cdim(L) with floor(log2 |L|) mistakes, plus a trade-off for infinite classes and noisy extensions.
-
Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.