enterprise search developers

Abstract: Knowledge graphs are a core component of today's knowledge infrastructure, supporting reasoning and anchoring knowledge systems to verifiable facts. RDF stores and SPARQL engines fulfill this function, enabling a range of retrieval and inference tasks on structured knowledge. Coupling them with Language Models (LMs) extends RAG toward neurosymbolic reasoning, where structured queries gate or re-rank generative outputs. This line of reasoning requires that SPARQL evaluation natively support tensor operations on dense embeddings, enabling multimodal querying and learned similarity-based ranking to be expressed together with graph-structural constraints. This approach is feasible only if the engine can efficiently perform dense vector search. We present QLever-Unified Indexed Vector Embedding Retrieval (QUIVER), an extension to QLever that adds native support for dense vector retrieval within RDF knowledge graphs. It implements three optimizations: engine-level registration of tensor functions, vocabulary-time parsing of JSON-encoded vectors, and a virtual SERVICE that exposes a vector index inside the query. We propose two new benchmarks: an extension of Berlin Sparql Benchmark (BSBM) with text embeddings and an extension of DBpedia with image embeddings. Against the baselines, vocabulary-time parsing alone yields median speedups of up to 41.9x on BSBM and 20x on DBpedia for single-type ranking; adding an approximate nearest-neighbor index yields speedups of 355x on BSBM and 97.8x on DBpedia. The index further makes cross-modal vector joins on DBpedia feasible in seconds, whereas all non-indexed configurations time out.

Abstract: Recent work has shown that fine-tuning decoder-only large language models (LLMs) for retrieval yields strong first-stage retrievers, with effectiveness improving as backbones grow in size. However, every query and document must pass through the full model, so encoding cost increases with model size. Mixture-of-Experts (MoE) LLMs activate only a subset of parameters per token and are widely used to scale generative models, yet remain underexplored as retrievers. We systematically study MoE backbones for retrieval by training MoE and dense LLMs from several families using the same procedure, evaluating them across diverse datasets, and measuring query encoding time under the same serving configuration. We show that MoE retrievers outperform dense retrievers with comparable active parameter counts by up to 3.0 nDCG@10 points on BEIR. One of our strongest MoE retrievers matches an 8B dense retriever with 59% fewer active parameters and 18% lower query encoding time. We further show that the number of experts used for query encoding can be reduced without retraining or re-indexing, retaining more than 99% of retrieval effectiveness while reducing query encoding time by up to 26%. Recent rerankers provide only modest additional gains over strong MoE first stages, which often match or exceed the reranked configurations we evaluate. Together, these results show that MoE LLMs can be strong and efficient first-stage retrievers.

Abstract: Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage and query-time interaction costs make large-scale deployment expensive. Pooling document tokens before indexing offers a natural remedy, yet static pooling must decide which visual evidence to preserve before the query is known. We study an alternative: a heavily compressed hot-path index generates candidates, after which query-aware token budgeting operates on the original token sets of the shortlisted pages. We formulate this stage-two selection as a budgeted MaxSim coverage problem, show that a clipped version is monotone submodular, and compare coverage-only, cluster-guided, token-wise, and marginal-gain policies. On ten ViDoRe tasks with ColModernVBERT, direct static pooling reduces macro normalized discounted cumulative gain at rank five from 0.6309 without compression to 0.4738 at a thirty-two-fold pool factor. Under the same candidate-generation regime and a pool-factor-eight-equivalent reranking budget, token top-k recovers 93.93 percent of the full-token score, while greedy marginal-gain selection recovers 98.39 percent. Held-out and leave-one-dataset-out evaluations yield positive greedy improvements over token top-k on every dataset. The latency analysis reveals two useful operating points: token top-k for interactive retrieval and the naive greedy implementation as a quality upper envelope. Together, these results show that late-interaction visual retrieval benefits from query-aware allocation rather than query-agnostic pooling alone.