Abstract:Significant progress has been made in aligning LLMs with target value functions. We argue that, even when an LLM has been well aligned in (post-)training, it may still fail to maximise the aligned value in reasoning. We mathematically formalise this gap as rational value risk: the utility discrepancy between a model's deployed reasoning strategy and its rational counterpart, which is defined to be the responses that maximise expected utility in the steepest direction. The estimation error of rational value risk is further decomposed into three components from finite candidates, finite prompts, and imperfect verifiers. Extensive experiments are conducted, covering models Llama-3.1, Qwen-2.5, T{\"}ulu-3 families (7B-72B), GPT-5.2, GPT-5.5, and DeepSeek-V4, and benchmarks UltraFeedback, AlpacaEval, GSM8K, MATH, HumanEval, and MathArena. The results validate that (1) rational value risk is widespread; (2) value alignment can reduce, but cannot eliminate, it; (3) the risk is highly sensitive to inference-time reasoning strategy; and (4) longer reasoning improves rationality with diminishing returns. The code is at this https URL.
From: Fengxiang He [view email]
[v1]
Tue, 26 May 2026 14:26:11 UTC (225 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。