Xiaohongshu Tech REDtech
Apr 10, 2024 · Artificial Intelligence
Early‑Stopping Self‑Consistency (ESC): Reducing Sampling Cost for Large Language Model Reasoning
Early‑Stopping Self‑Consistency (ESC) dynamically halts sampling once a sliding‑window answer distribution reaches zero entropy, cutting the number of required LLM reasoning samples by 34‑84 % across arithmetic, commonsense, and symbolic benchmarks while preserving accuracy and offering a theoretically‑bounded, robust, budget‑adaptive alternative to traditional Self‑Consistency.
AIChain-of-ThoughtEarly-Stopping
0 likes · 14 min read