← 研踪 PaperTrailarXiv:2611.26332 · v1
Rigel-Ladon: An Option-Count Law for a One-Pass Decision Encoder, Tested on Held-Out Option Counts and Held-Out Schemas
首次提交 2026-11-20 00:12
版本更新 2026-11-20 00:12
雷达观测 2026-11-20 14:52
摘要
Laya is a small neural network that reads a text, a question and K written options, and returns one probability per option in a single pass. We ask how its accuracy falls as K grows from 2 to 35 and whether that can be predicted. We score nested option sets (every K-option question contains the smaller ones) on four question pools, for the released model (Base) and our fine-tune (FT), and score every item against each single rival. FT trained on one 12-option topic question (in-family); a 12-option HR (department-routing) question is out-of-family. Logit accuracy (the log of correct over incorrect answers) is linear in log(K-1) with slope 0.68 to 0.88. Fitted on K up to 6, the law predicts K=7 to 12 within 0.6 points and K up to 24 within 1.2 (a log-linear rule: 1.6 and 6.7). Taking the slope from the topic question and measuring only two-option accuracy on HR predicts its other K within 0.3 points (FT) and 0.7 (Base). On a 35-label pool of five schemas the law fails (5 to 11 points). Independence of irrelevant alternatives is rejected: the gold-versus-rival log-odds shifts by +0.24 to +2.07 nats per doubling of K, yet pairwise answers reproduce K-way accuracy within 4.7 points. Order averaging (averaging over several orderings of the options), shortlists, a temperature law and calibrated prediction sets did not transfer (FT's 90% sets cover 84% on HR). 2 of 10 predictions made in advance held. Caveats: one model family and LLM-labelled synthetic text.
作者备注:43 pages, 29 figures, 35 tables
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-20 00:12 · 最新观测版本
Rigel-Ladon: An Option-Count Law for a One-Pass Decision Encoder, Tested on Held-Out Option Counts and Held-Out Schemas
Laya is a small neural network that reads a text, a question and K written options, and returns one probability per option in a single pass. We ask how its accuracy falls as K grows from 2 to 35 and whether that can be predicted. We score nested option sets (every K-option question contains the smaller ones) on four question pools, for the released model (Base) and our fine-tune (FT), and score every item against each single rival. FT trained on one 12-option topic question (in-family); a 12-option HR (department-routing) question is out-of-family. Logit accuracy (the log of correct over incorrect answers) is linear in log(K-1) with slope 0.68 to 0.88. Fitted on K up to 6, the law predicts K=7 to 12 within 0.6 points and K up to 24 within 1.2 (a log-linear rule: 1.6 and 6.7). Taking the slope from the topic question and measuring only two-option accuracy on HR predicts its other K within 0.3 points (FT) and 0.7 (Base). On a 35-label pool of five schemas the law fails (5 to 11 points). Independence of irrelevant alternatives is rejected: the gold-versus-rival log-odds shifts by +0.24 to +2.07 nats per doubling of K, yet pairwise answers reproduce K-way accuracy within 4.7 points. Order averaging (averaging over several orderings of the options), shortlists, a temperature law and calibrated prediction sets did not transfer (FT's 90% sets cover 84% on HR). 2 of 10 predictions made in advance held. Caveats: one model family and LLM-labelled synthetic text.
查看此版本解读 →查看此版本原文 ↗