重新將人類置於LLM個人化的中心

摘要

儘管興趣日增，目前對大型語言模型（LLMs）個性化能力的大多數評估仍依賴合成數據。現有個性化系統對真實使用者的成效仍不明確。本文探討LLM在使用合成數據與人類數據時，在個性化表現上的差距。我們收集了人類對話（550段對話）及三個個性化階段的判斷：從對話中提取使用者屬性（5,949項判斷）、將相關屬性配對至新提示（11,919項）、以及將相關屬性納入個性化回應（1,101項）。納入人類數據後，揭示了系統在各階段的局限性。模型難以從人類對話中提取屬性，與人類對相關屬性的判斷不一致，且產生的個性化回應被人類評定為不比通用回應更好（儘管LLM自身廣泛評定為更佳）。我們引入兩種輕量級基於訓練的干預措施，在我們的前兩個階段中將自動化個性化評估更貼近人類數據。然而，在第三階段我們發現，學習到的獎勵模型與人類評分的相關性僅為中等，這表明與人類對齊的個性化品質判斷難以直接建模。我們收集的數據為研究模型應如何以人類認為有用的方式提取、選擇並納入使用者資訊提供了基礎。

English

Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data. It remains unclear how well current personalization systems work for real users. In this paper, we study the gap in LLM personalization performance when using synthetic versus human data. We collect human conversations (550 conversations) and judgments across three stages of personalization: extracting user attributes from conversations (5,949 judgments), pairing relevant attributes with new prompts (11,919), and incorporating relevant attributes into a personalized response (1,101). Incorporating human data reveals system limitations at each stage. Models struggle to extract attributes from human conversations, disagree with human judgments on relevant attributes, and generate personalized responses that humans judge no better than generic responses (though that LLM judges widely rate as better). We introduce two lightweight training-based interventions that shift automated personalization evaluation closer to human data in our first two stages. However, in our third stage we find that learned reward models achieve only modest correlation with human ratings, suggesting that human-aligned personalization quality judgments are difficult to model directly. Our collected data provides a foundation for studying how models should extract, select, and incorporate user information in ways that humans find useful.