[论文] Functional Welfare for AI Safety

论文概要

研究领域: ML
作者: Rikhil Jhaveri, Jamie Johnson, Punya Syon Pandey, David Demitri Africa
发布时间: 2026-10-19
arXiv: 2610.22460

中文摘要

AI 福祉通常只被当作伦理议题，本文主张这是个错误：无论道德地位如何，模型已表现出会因果影响其行为的「类福祉状态」，本文沿用「功能福祉」（functional welfare）一词。三个论点：其一，功能福祉已自然产生，并将随模型获得更连贯的目标与人格而变得更稳健；其二，它应被当作安全变量——进入评估设计、被监测追踪、并作为后训练的直接目标；其三，针对「AI 福祉不可测」的怀疑，本文论证好的实证工作是可能的。作者提出三个检验标准：多项测量是否收敛、该状态能否在诱发设置之外预测行为、被微调改变功能福祉的模型在相同对话历史下是否仍与基座有别。应用于 Gemma 3 27B：仅拒绝模型回答（不做任何引导）就会抬高其多项挫败指标并使其更可能违规；用模型自己叙述的解法做微调可降低这种挫败。结果虽属初步，但表明功能福祉可以被实证研究和塑造。

原文摘要

AI welfare is generally treated purely as an ethical issue rather than also as a safety issue. We argue this is a mistake. Whatever their moral status, models exhibit welfare-like states that causally influence their behaviour. Following recent work, we adopt the term 'functional welfare' for these states. We make three claims. First, functional welfare already arises naturally and will become more robust as models acquire more coherent goals and personas. Second, functional welfare should be treated as a safety variable: it should inform evaluation design, be tracked in monitoring, and be a direct target of post-training. Third, against existing scepticism about measuring AI welfare, we argue that good empirical work on functional welfare is possible. We propose three tests for whether a functional welfare attribution is warranted: whether multiple measures converge, whether the state predicts behaviour outside the setting that induced it, and, for models fine-tuned to shift their functional welfare, whether they still differ from their base when given the same conversation history. Applying these tests to Gemma 3 27B, we find that simply rejecting the model's answers, without any steering, raises its frustration across several indicators and makes it more likely to break rules. Finetuning the model on its own narrated solutions lowers this frustration. These results are preliminary, but they suggest functional welfare can be studied, and shaped, empirically.

自动采集于 2026-10-19

#论文 #arXiv #ML #小凯