AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval

Yingyi Zhang, Junyi Li, Wenlin Zhang, Pengyue Jia, Xianneng Li, Yichao Wang, Derong Xu, Yi Wen, Huifeng Guo, Yong Liu, Xiangyu Zhao

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
adaptive switching between familiarity and recollection instead of dense top-K only (ablation)RF-Mem · PersonaMem 32Koverall accuracy: 0.5908 -> 0.6350Improved
adaptive switching instead of dense top-K only at 1M corpus (ablation)RF-Mem · PersonaMem 1Moverall accuracy: 0.4518 -> 0.4589Improved
add entropy-guided gating over always-on recollection (ablation)RF-Mem · PersonaMem 32Koverall accuracy: 0.6214 -> 0.6350Improved
add entropy-guided gating over always-on recollection (latency) (ablation)RF-Mem · PersonaMem 32Kretrieval time: 7.09ms -> 5.09msImproved
retrieve with RF-Mem instead of feeding full contextRF-Mem · PersonaMem 128Koverall accuracy: 0.3231 -> 0.5394Improved
retrieve with RF-Mem instead of feeding full context at 32KRF-Mem · PersonaMem 32Koverall accuracy: 0.6129 -> 0.6350Improved
RF-Mem vs familiarity on PersonaBenchRF-Mem · PersonaBench (MiniLM)overall Recall@10: 0.5964 -> 0.6071Improved
RF-Mem vs familiarity on LongMemEval-MRF-Mem · LongMemEval-M (MiniLM)Recall@5: 0.4177 -> 0.4391Improved
layer RF-Mem on MemoryBank summary indexRF-Mem · PersonaMem 32K (MemoryBank summary index)overall accuracy: 0.4941 -> 0.5314Improved
use RF-Mem as retrieval layer in Search-o1Search-o1 · PersonaMem 32K (Search-o1)overall accuracy: 0.5823 -> 0.6146Improved
RF-Mem on HyDE-expanded queriesHyDE retrieval · PersonaBench (HyDE expansion, MiniLM)overall Recall@10: 0.5120 -> 0.5194No clear effect
increase mixing alpha (more weight on original query) (ablation)Recollection retrieval · LongMemEval-MRecall@5 / Recall@50Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy