search system engineers

Abstract: Reciprocal Rank Fusion (RRF) is widely used to combine sparse and dense retrievers in hybrid information retrieval, but a critical limitation is that it assigns a fixed, uniform weight to each retriever regardless of the query. Query-aware methods treat the per-query optimal weight as a single point, an assumption whose empirical validity has not been examined. We present an empirical study of eight dynamic fusion weight prediction strategies across four datasets and four sparse--dense retriever pairs. When we compare these approaches to static fusion and a per-query oracle that bounds achievable performance, several findings emerge. First, the per-query optimal fusion weight is typically an interval rather than a point. Queries can have multiple optimal intervals, and these can take on a variety of shapes. Second, 74 of 128 dynamic fusion methods tested were significantly better than standard RRF after false discovery rate correction. Third, dynamic fusion methods exhibit differing quality and latency characteristics that should be considered when choosing an appropriate fusion method. To address this last finding, we present a tiered decision framework that maps practitioner constraints, dataset properties, label availability, hardware, and latency budget to an appropriate method class. We release the code for our experiments at https://github.com/thomsonreuters/query-based-rrf.

Abstract: Retrieval-augmented generation (RAG) mitigates hallucinations and knowledge staleness in large language models using external knowledge. However, ingestion from public and third-party sources exposes RAG systems to poisoning attacks. Existing attacks are designed and evaluated under exact retrieval, where poisoned documents participate in global ranking. Deployment-scale systems instead rely on approximate nearest-neighbor (ANN) indexes such as hierarchical navigable small world (HNSW), where limited search budgets, graph-search reachability, and local benign-document competition invalidate this assumption and degrade existing attacks. We present a topology-aware topic-level poisoning attack against large-scale HNSW-RAG that generalizes to unseen topic queries. We organize poisoned documents into a Hub-Satellite structure: Satellites provide competitive entry points across semantic regions, while Hubs strengthen local cohesion and facilitate cascading retrieval. For generation, we propose an entity-claim promotion attack combining evidence anchoring and entity-claim coupling to promote the target entity via a target claim across different query regions. On 2M-document Wikipedia, our attack maintains over 72% retrieval success and reaches 31.29% attack success, substantially outperforming baselines; domain-specific experiments further support its effectiveness. Structural analyses show that the Hub-Satellite topology forms in HNSW, indicating that graph structure contributes to improved poisoned-document retrieval. Existing poisoning defenses cannot mitigate the attack, exposing graph-structural risks in HNSW-RAG systems.

Abstract: Filtering search is one of the crucial applications of approximate nearest neighbor search (ANNS). In filtering search, label information is used in conjunction with unstructured vector data. ANNS provides efficient similarity search in large-scale datasets, however, the memory footprint of storing both vector data and their associated label becomes a significant cost factor as dataset sizes grow. To address this problem of increasing DRAM usage, we propose AiSAQ-in-Filtering, with a novel quantization method called LiPQ (Label-inclusive Product Quantization). LiPQ combines unstructured data and structured labels into a single representation, leading no growth of encoded data. Our proposal increased recall@1 of single-label searches by up to 55% and fewer disk I/Os compared with existing methods. This also retains the main advantages of AiSAQ, which can reduce DRAM footprint by up to 1/78 and index switching time comparing with existing methods. This proposal can also be applied to sparse-dense hybrid search beyond label filtering such as semantic and keyword search of documents.

Abstract: Parallel search may generate a correct answer that final-answer voting fails to select. We formulate this consolidation stage as trajectory selection and introduce TRACE (Trajectory Ranking with Aggregated Cross-Rollout Evidence), a lightweight learned selector that ranks completed trajectories using the search evidence behind their answers. TRACE preserves individual query and evidence occurrences, connects rollouts through shared content or document identity, and propagates information across these relations. Each candidate answer then reads the updated states of its own trajectory, preserving retrieval provenance while incorporating evidence from related rollouts. Trained with answer-level supervision over frozen text embeddings, TRACE returns an existing answer without additional search or autoregressive aggregation. One selector per search setting transfers across rollout policies and agent backbones without agent-specific fine-tuning, improving over voting across six WebQA policies and six long-horizon dataset-backbone combinations at $K=16$. On Qwen2.5-14B Base/SFT WebQA pools, TRACE achieves 45.2/49.2% EM, compared with 43.9/48.0% for the strongest Qwen3-32B generative aggregators. On long-horizon FRAMES, GAIA, and BrowseComp, it reaches 78.6% average accuracy, exceeding majority voting by 3.1 percentage points. On Base WebQA pools, TRACE with only 8 rollouts comes within 0.4 points of majority voting over 64. TRACE also achieves at least $10\times$ higher processing throughput than SolAgg, SummAgg, and AggAgent across all seven WebQA benchmarks. These results show that reusing cross-rollout search evidence provides an effective and efficient alternative to heavyweight generative aggregation for parallel search. Code is available at https://github.com/Jaasssoooonnnnn/TRACE.