---
title: "通过选择性预测对齐大语言模型"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.03528v1"
permalink: "https://feed.astralor.com/items/itm_489579d3c09e0dc7eae3669a"
published: "2026-07-03T17:59:02.000Z"
score: 78
channel: "ai"
tags: ["Google DeepMind","RLSR","大语言模型对齐","选择性预测"]
---

# 通过选择性预测对齐大语言模型

## AI 点评

> 这篇论文巧妙地将选择性预测带入了LLM对齐的视野，不再只盯着正确率。如果你在做模型部署或可靠性工程，RLSR的思路很值得参考——它让模型学会“何时闭嘴”，而不是强行输出错误答案。对AI安全从业者和高容错场景开发者尤其有启发。

## 速览

本文提出一种新的对齐框架RLSR（强化学习选择奖励），旨在通过优化风险-覆盖率曲线下面积（AURC）来提升大语言模型的选择性预测能力。该方法让模型仅在可能正确的输入上做出预测，从而降低错误率，实现更可靠的人机协作。实验表明，RLSR在领域内和领域外任务上均优于多种现有对齐方法。

## 关键点

- 选择性预测通过只对可信输入进行预测来平衡风险与覆盖率，提升LLM可靠性。
- 现有对齐方法侧重正确性或校准指标，本文首次将AURC作为对齐目标。
- RLSR框架利用强化学习直接优化AURC，实现更优的风险-覆盖率权衡。

## 全文

Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reliability a foremost practical concern. In this paper, we focus on enhancing LLM reliability through selective prediction (SP), a strategy that allows an LLM to only predict for inputs where it is likely to be correct (i.e., coverage) and hence reduce the error rate (i.e., risk) on that portion of inputs -- flagging the remaining inputs for future human discretion. In other words, SP improves LLM reliability by balancing the risk-coverage trade-off and enabling seamless human-AI collaboration. To integrate SP into LLMs, we focus on the LLM post-training alignment stage and propose to align LLMs with SP performance metrics, in contrast with existing LLM alignment methods that focus primarily on correctness or calibration metrics. Specifically, we propose a novel alignment framework, Reinforcement Learning for Selection Reward (RLSR), which targets the area under the risk-coverage curve (AURC) -- a popular SP performance metric -- as its alignment objective. RLSR achieves substantially better risk-coverage trade-off compared to multiple alignment baselines on both in-domain and out-of-domain tasks.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_489579d3c09e0dc7eae3669a