跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.25003 · v1

A Model of Diverse Sampling from Language Models

首次提交 2026-11-19 01:56
版本更新 2026-11-19 01:56
雷达观测 2026-11-21 12:18
arXiv ↗PDF ↗

摘要

Language models often produce high-quality individual samples but poor sets, with repeated samples clustering around the same semantic modes. We formalize diverse generation as sampling a size-KK subset of complete strings from a determinantal point process (DPP), where the likelihood encodes item quality, and the embedding geometry encodes repulsion between similar outputs. Exact inference over all strings is intractable, so we propose PoolDPP: draw a finite candidate pool from a tractable proposal, importance-weight the candidates toward the target quality, and run a KK-DPP sampler on the induced pool kernel; a greedy MAP variant provides deterministic selection. We prove a finite-sample bound with an explicit constant: the KL divergence between the sampler's output and the target KK-DPP decays as O(1/N) in the pool size. Empirically, PoolDPP extends the quality--diversity frontier on open-ended generation and the precision--recall frontier on ambiguous text-to-SQL (Ambrosia), and on mathematical reasoning (GSM8K), it raises diversity at about the same pass@KK.

作者备注:NeurIPS 2026 paper

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 01:56 · 最新观测版本

A Model of Diverse Sampling from Language Models

Language models often produce high-quality individual samples but poor sets, with repeated samples clustering around the same semantic modes. We formalize diverse generation as sampling a size-KK subset of complete strings from a determinantal point process (DPP), where the likelihood encodes item quality, and the embedding geometry encodes repulsion between similar outputs. Exact inference over all strings is intractable, so we propose PoolDPP: draw a finite candidate pool from a tractable proposal, importance-weight the candidates toward the target quality, and run a KK-DPP sampler on the induced pool kernel; a greedy MAP variant provides deterministic selection. We prove a finite-sample bound with an explicit constant: the KL divergence between the sampler's output and the target KK-DPP decays as O(1/N) in the pool size. Empirically, PoolDPP extends the quality--diversity frontier on open-ended generation and the precision--recall frontier on ambiguous text-to-SQL (Ambrosia), and on mathematical reasoning (GSM8K), it raises diversity at about the same pass@KK.

查看此版本解读 →查看此版本原文 ↗