Best AI News — Updated Every 3 Hours
Story Page
← All Stories
Home Papers Story
Papers

Format Sensitivity Index: Token-Controlled Prompt Wrapper Robustness and Schema Compliance in LLM Benchmarking

Via ArXiv cs.AI
Tuesday, Jul 14, 2026 · 4:00AM
Summary

arXiv:2607.09665v1 Announce Type: new Abstract: Prompt wrappers often differ only in formatting, yet they can change model scores enough to flip leaderboard conclusions. We study this variance under a token-controlled protocol and introduce two complementary metrics: the Format Sensitivity Index (FS

Continue reading the full article
Read at ArXiv cs.AI
arxiv.org
Back to all stories