English(EN) Adaptive Personalization Under Preference Epistemic Uncertainty

语言模型难以适应对话中不断变化的用户偏好

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-02 05:00

研究人员开发了一个新的基准来评估语言模型在对话式AI中适应不断变化的人类偏好的能力。该基准包含250个跨五种语言的个性化角色和25,000个对话轮次，揭示了模型识别恰当策略的能力与其生成策略的能力之间存在显著差距。虽然模型在提供选项时能够识别正确的策略，但在开放式生成中，它们倾向于利用现有偏好，策略校准下降了35-46%。针对条件化人类偏好的定向训练可以提高模型性能，将用户可接受性差距缩小三分之一，以应对分布外角色和对话风格。 AI

影响强调了当前LLM在动态用户偏好适应方面的关键局限性，表明需要改进训练方法。

排序理由研究论文，详细介绍了新的基准和关于语言模型行为的发现。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 1 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了新的基准和关于语言模型行为的发现。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Priyanka Dey, Rajarshi Das, Vikas Bahirwani, Qi Zeng, Julia Kruk, Qi Qi · 2026-11-02 05:00

Adaptive Personalization Under Preference Epistemic Uncertainty

arXiv:2610.40930v1 Announce Type: new Abstract: Human preferences change over time: an established preference may remain valid over time, become uncertain as context shifts, or be explicitly revised. Effective personalization requires conversational AI to adapt its response strat…

本文如何被排名

报道来源 [1]

Adaptive Personalization Under Preference Epistemic Uncertainty

相关实体

相关话题