Tag
This paper proposes a training-free, CPU-only retrieval method that fuses BM25 lexical scores with late-interaction dense scores for conversational memory retrieval, achieving up to +17.2 points improvement on LoCoMo Hit@1 over late interaction alone across six encoders. The study provides controlled ablations on pooling operators, reranker effects, and benchmark robustness, framing the gain as a division of labor between dense and lexical signals.