paper

Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs

paperactiveprovisionaltowards-root-memories-benchmarking-and-enhancing-implicit-logical-memory-retrieval-for-personalized-llms-27ecdcf4·1 events·first seen 4h ago

Aliases: Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs

Co-occurring entities

IMLogic RootMem

More like this (12)

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It Personal Visual Memory Benchmark A sleep-like consolidation mechanism for LLMs Long-context Reasoning Benchmarks Memory Insights Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs Learning from the Self-future: On-policy Self-distillation for dLLMs SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model FlashbackCL: Mitigating Temporal Forgetting in Federated Learning Clinically Grounded Privacy Evaluation of Medical LMs Reasoning in Memory (RiM)

Recent events (1)

5arXiv · cs.CL·4h ago·source ↗

IMLogic benchmark and RootMem framework target implicit logical memory retrieval for personalized LLMs

Researchers introduce IMLogic, a benchmark for evaluating implicit logical memory retrieval in long-dialogue personalized LLM scenarios, addressing gaps in existing semantic-similarity-based retrieval methods. They also propose RootMem, a plug-and-play framework that distills user histories into structured 'root memories' and uses an LLM-based router to activate logically relevant memories alongside semantic retrieval. Experiments show RootMem outperforms retrieval baselines and improves existing memory agents. The work targets a concrete weakness in current personalized LLM memory systems where logically critical memories lack semantic overlap with queries.

Evaluation and Benchmarking Agent and Tool Ecosystem Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs IMLogic RootMem