RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models

Open paper
Benchmark Model Rank Results
question-answering-on-duorcVector Database (ChromaDB)#1Accuracy: 55.71
question-answering-on-duorcHybrid-RecallM#2Accuracy: 52.68
question-answering-on-duorcRecallM#3Accuracy: 48.13

Rank counts only results with a code link.