Re-Centering Humans in LLM Personalization
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 ...
| Authors | Lechen Zhang, Jiarui Liu, Tal August |
|---|---|
| Primary category | cs.CL |
| Published | 4 June 2026 |
| Last updated at source | 4 June 2026 |
Connected in the knowledge graph
- leczhang/recenter-personalizationDataset · cited by
- leczhang/recenter-personalization-stage2-grpoModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.