Eri Hayashi

Do Personalized LLMs Need the Whole Conversation? Matching the Full History with Only 5% of Its Text via Relevance-Filtered Context

Personalized assistants accumulate long conversation histories, and passing the whole history to an LLM with every request is costly. We show that it is also unnecessary. On PersonaMem-v2 (180 questions), with GPT-5.6-terra and Claude Opus 5.5 as judges, a relevance-filtered context, built by sentence-level retrieval t...