Prompt-conditioned LLMs face irreducible error floors from language's limited information capacity and alignment constraints, proven via PAC-Bayes bounds on bilevel cheap-talk games for certain task families.
The learnability of in-context learning.arXiv preprint arXiv:2303.07895,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
Prompt-conditioned LLMs face irreducible error floors from language's limited information capacity and alignment constraints, proven via PAC-Bayes bounds on bilevel cheap-talk games for certain task families.