COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation
arXiv:2609.26853v1 Announce Type: new Abstract: While Large Language Models (LLMs) have achieved remarkable results across various benchmarks, their alignment with normative values often results in homogenized responses that fail to address diverse user preferences. Existing training-free methods o…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-24 04:00 · arXiv cs.LG
COPE: Continual Personalization of LLMs under Sparse User Feedback via User Embeddings and Self-Evaluation