Selroute: Query-type-aware Routing For Long-term Conversational Memory Retrieval

Abstract

Retrieving relevant past interactions from long-term conversational memory typically relies on large dense retrieval models (110M-1.5B parameters) or LLM-augmented indexing. We introduce SelRoute, a framework that routes each query to a specialized retrieval pipeline -- lexical, semantic, hybrid, or vocabulary-enriched -- based on its query type. On LongMemEval_M (Wu et al., 2024), SelRoute achieves Recall@5 of 0.800 with bge-base-en-v1.5 (109M parameters) and 0.786 with bge-small-en-v1.5 (33M parameters), compared to 0.762 for Contriever with LLM-generated fact keys. A zero-ML baseline using SQLite FTS5 alone achieves NDCG@5 of 0.692, already exceeding all published baselines on ranking quality -- a gap we attribute partly to implementation differences in lexical retrieval. Five-fold stratified cross-validation confirms routing stability (CV gap of 1.3-2.4 Recall@5 points; routes stable for 4/6 query types across folds). A regex-based query-type classifier achieves 83% effective routi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymckee2026selroute

Related papers

• CITADEL: Conditional Token Interaction Via Dynamic Lexical Routing For Efficient And Effective Multi-vector Retrieval (2022)13.05
• Routerretriever: Routing Over A Mixture Of Expert Embedding Models (2024)0.00
• DS@GT At TREC TOT 2025: Bridging Vague Recollection With Fusion Retrieval And Learned Reranking (2026)0.00
• RETRONLU: Retrieval Augmented Task-oriented Semantic Parsing (2021)3.58
• Towards Dynamic Dense Retrieval With Routing Strategy (2026)0.00
• SLQ: Bridging Modalities Via Shared Latent Queries For Retrieval With Frozen Mllms (2026)0.00
• Your Dense Retriever Is Secretly An Expeditious Reasoner (2025)0.00
• Lexsembridge: Fine-grained Dense Representation Enhancement Through Token-aware Embedding Augmentation (2025)2.35