跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25168 · v1

What a Calibrated Probability Hides: Belief-Level Post-Training for Decision Models

首次提交 2026-11-19 04:48
版本更新 2026-11-19 04:48
雷达观测 2026-11-21 12:18
arXiv ↗PDF ↗

摘要

A calibrated decision model can predict how often each answer is chosen. The same prediction can reflect disagreement among people who are confident in their choices or uncertainty among people who share a belief. Disagreement calls for identifying whose perspective applies, while uncertainty calls for gathering more evidence. Standard post-training scores a single prediction against one observed choice at a time, learning the pooled distribution without distinguishing these two sources of uncertainty. We introduce Belief-Grouped Policy Optimization (BGPO). The policy proposes a list of beliefs, estimates their prevalence, and predicts a choice distribution for each. During training, BGPO uses Bayes' rule to estimate how likely each belief was to generate an observed choice. These estimates weight the choice's contribution to each belief's log-score reward. To discover rare beliefs, the policy also proposes lists after seeing a few observed choices and retains them only if they predict held-out choices well. At inference, the policy uses only the question and combines the belief-specific distributions by prevalence to produce a calibrated aggregate prediction. On benchmarks covering opinions, conversation safety, emotions elicited by artwork, and photo aesthetics, BGPO achieves the lowest conditional, worst-group, and overall Jensen-Shannon divergence across model initializations. It improves conditional divergence on both text and image tasks. On a synthetic image task with known beliefs, BGPO recovers the underlying groups more accurately than baselines trained with belief labels.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

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 · 2026-11-19 04:48 · 最新观测版本

What a Calibrated Probability Hides: Belief-Level Post-Training for Decision Models

A calibrated decision model can predict how often each answer is chosen. The same prediction can reflect disagreement among people who are confident in their choices or uncertainty among people who share a belief. Disagreement calls for identifying whose perspective applies, while uncertainty calls for gathering more evidence. Standard post-training scores a single prediction against one observed choice at a time, learning the pooled distribution without distinguishing these two sources of uncertainty. We introduce Belief-Grouped Policy Optimization (BGPO). The policy proposes a list of beliefs, estimates their prevalence, and predicts a choice distribution for each. During training, BGPO uses Bayes' rule to estimate how likely each belief was to generate an observed choice. These estimates weight the choice's contribution to each belief's log-score reward. To discover rare beliefs, the policy also proposes lists after seeing a few observed choices and retains them only if they predict held-out choices well. At inference, the policy uses only the question and combines the belief-specific distributions by prevalence to produce a calibrated aggregate prediction. On benchmarks covering opinions, conversation safety, emotions elicited by artwork, and photo aesthetics, BGPO achieves the lowest conditional, worst-group, and overall Jensen-Shannon divergence across model initializations. It improves conditional divergence on both text and image tasks. On a synthetic image task with known beliefs, BGPO recovers the underlying groups more accurately than baselines trained with belief labels.

查看此版本解读 →查看此版本原文 ↗