Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice Evaluation
Paper recorded by Signals 4 on 2026-10-07 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-07 on arXiv · recorded by Signals 4 on 2026-10-08
Category: cs.CL · 自然语言处理 · first seen 2026-10-08
Abstract
Adaptive computation aims to improve language-model inference by tailoring execution to each input. For layer programs, oracle evaluations use known answers to estimate the potential gain from this flexibility, before a practical selector is available. However, a gain from selection does not by itself explain why the chosen programs help. This study examines this distinction using 32 layer-skippin
Read on arXiv →
Cite this page: Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice Evaluation: the #299 most recent of 660 cs.CL papers we have recorded (as of 2026-10-07). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/input-blind-controls-produce-substantial-oracle-headroom-for-layer-programs-in-m.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free