Papers/2609.12111
🧪 Test?View on arXiv

The Cost of Compression: A Rate-Distortion Limit on Factual Hallucination

Not provided in the abstract

compressionfactual recalllanguage modelsinformation theory
2609.12111
Builder Relevance
70%
2h ago

Abstract

This paper explores the dual sources of error in factual hallucination during closed-book question answering, focusing on the impact of finite memory and compression on factual recall.

Reality Card

Core Claim

The study establishes a rate-distortion limit on factual hallucination, demonstrating that both compression distortion and missing coverage contribute to errors in factual recall.

Method / Result

The derived bound shows that the expected error in factual recall can be quantified as a function of observed facts and memory constraints.

Limitations

The results are theoretical and may not fully capture the complexities of real-world language models, limiting direct applicability.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers