2026-06-08原文2 min readUpdated: 2026-06-08

Re-Centering Humans in LLM Personalization

This study reveals significant gaps between synthetic and human data in evaluating LLM personalization, showing models struggle in attribute extraction, selection, and response generation. Two lightweight interventions improve automated evaluation, but human-aligned quality judgments remain challenging.

SourcearXiv Computational LinguisticsAuthor: Lechen Zhang, Jiarui Liu, Tal August

[2606.06614] Re-Centering Humans in LLM Personalization

[Submitted on 4 Jun 2026]

Title:Re-Centering Humans in LLM Personalization

View a PDF of the paper titled Re-Centering Humans in LLM Personalization, by Lechen Zhang and 2 other authors

View PDF HTML (experimental)

Abstract: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.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)

Cite as: arXiv:2606.06614 [cs.CL]

(or arXiv:2606.06614v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.06614

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Lechen Zhang [view email] [v1] Thu, 4 Jun 2026 18:04:47 UTC (1,040 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Re-Centering Humans in LLM Personalization, by Lechen Zhang and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-06

Change to browse by:

cs cs.AI cs.HC

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)