Paper

Re-Centering Humans in LLM Personalization

Unreadunread

AI summary

arXiv:2606. 06614v1 Announce Type: new Abstract: Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data.

Reading status

Priority

About this paper

Authors: Lechen Zhang, Jiarui Liu, Tal August
Released: 2026-06-08 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because Re-Centering Humans in LLM Personalization overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)", clean result "Only continuous soft prefixes hit both EM axes at once on Qwen-2.5-7B-Instruct: discrete prompt searches split between the alignment objective and the distributional objective, and both discretizations of the soft prefix collapse (MODERATE confidence)". Matching terms: persona, rect, eval, rate, stage, language, model. Source: arxiv cs.CL (NLP).
arXiv: 2606.06614

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Re-Centering Humans in LLM Personalization. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.