LMs systematically inflate expressed certainty during rewriting, affecting up to 75% of outputs with a 1.5-2x bias toward increasing rather than decreasing certainty, and the effect compounds over iterations.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , month = jul, year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
LLM-driven program mutation converges to restricted structural attractors, with 87% of chains showing over 93% structural revisits and most variation limited to terminal substitutions, unlike classical GP.
LLM-based compression of financial source material can alter downstream investment decisions via decontextualization and model dependency, addressed by an agentic auditing approach that checks multiple compressions against the original.
citing papers explorer
-
Mutation Without Variation: Convergence Dynamics in LLM-Driven Program Evolution
LLM-driven program mutation converges to restricted structural attractors, with 87% of chains showing over 93% structural revisits and most variation limited to terminal substitutions, unlike classical GP.
-
When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis
LLM-based compression of financial source material can alter downstream investment decisions via decontextualization and model dependency, addressed by an agentic auditing approach that checks multiple compressions against the original.