danielle34/cavewoman

Caveman prompting, measured. A two-channel evaluation framework for prompt compression and LLM token efficiency: what input vs output compression costs in dollars, accuracy, and whether the reasoning changes. Compress the output not the prompt!! 9 models, 5 benchmarks, 10 languages. EMNLP 2026 Main

语言：Python · GitHub 星标：19 · Fork：1

话题：anthropic · benchmark · caveman · emnlp2026 · evaluation-framework · inference-cost · large-language-models · llm-evaluation

在 GitHub 上查看原仓库