other
Optimizing for the Rank Made the Corpus More Alike
CHASE simulates creators repeatedly rewriting documents toward one LLM ranking signal.
Published Updated Story ID: mp-2026-09-01-017
Summary
CHASE simulates creators repeatedly rewriting documents toward one LLM ranking signal.
Across six domains and twenty rounds, quality-ranking alignment fell in every domain, with a mean Spearman change of minus 0.068. A random-target control linked the shift to ranking incentives rather than repeated rewriting alone; the result is a controlled ecosystem simulation.
Why it matters
CHASE simulates creators repeatedly rewriting documents toward one LLM ranking signal.
Limits and context
No additional limitation was separately recorded.
Key claims
CHASE simulates creators repeatedly rewriting documents toward one LLM ranking signal.
Evidence: source-2026-09-01-019
Sources
- arXiv preprint 2608.30466arXiv · primary research
Corrections
No corrections have been recorded for this story.