[Link] The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts

The Perplexity Paradox: Why Code Compresses Better Than Math in LLM Prompts

arXiv:2602.15843v1 Announce Type: new Abstract: In "Compress or Route?" (Johnson, 2026), we found that code generation tolerates aggressive prompt compression (r >= 0.6) while chain-of-thought reasoning degrades gradually. That study was limited to HumanEval (164 problems), left the "perplexity...

🔗 Read more: https://arxiv.org/abs/2602.15843