Jul 2026· Annual International ACM SIGIR Conference on Research and Development in Information Retrieval· pp. 4052-4057· 0 citations· 34 references
Computer Science
TL;DR
This work investigates whether Learned Sparse Retrieval (LSR) can mitigate this backward compatibility issue, and explores lightweight query adaptation methods including ranking fusion, representation fusion, and minimal-training adapters to further improve compatibility.
Abstract
Advancements in retrieval models necessitate re-indexing, a computationally expensive process for large-scale production environments. While updating only the query encoder and continuing to use the old index could be a promising middle ground, dense retrieval systems suffer severe performance drops in this setting. We investigate whether Learned Sparse Retrieval (LSR) can mitigate this backward compatibility issue, as its lexical matching may provide a stable term-based anchor to preserve compatibility across model versions. Experiments on BEIR and the streaming settings of LoTTE show that upgrading only the query encoder causes only a small effectiveness drop in LSR when no mitigation applied, whereas dense retrieval fails severely. We explore lightweight query adaptation methods including ranking fusion, representation fusion, and minimal-training adapters to further improve compatibility. These approaches significantly improve backward compatibility on BEIR and effectively reduce performance loss in streaming retrieval. Code: https://github.com/JingfenQiao/LSR-BC.git
A unified pipeline deployed at Walmart that addresses both signal quality and model evolution is presented, and a Warm-Start Distillation technique that transfers domain-specific expertise from the legacy model to the new backbone is introduced.
Zhen Yang, Juexin Lin, Hongwei Shang et al.· Annual International ACM SIG...· 1 citation
This work introduces AnchorQE, a training-free method that separately encodes the original query and its expansion before interpolating them, and shows that AnchorQE improves retrieval effectiveness by up to 12.89% when compared to widely-used expansion-only or text-level concatenation baselines across TREC-DL, LoTTE, and BEIR.
In large-scale e-commerce retrieval, dual-encoder retrievers are op- timized for contrastive similarity, whereas downstream rerankers capture finer-grained relevance preferences; this objective mis- match limits end-to-end retrieval quality. Reinforcement Learning offers a way to use reward-model feedback for retriever adaptation, but we observe that standard policy-gradient updates can degrade embedding geometry, especially when the document index must remain frozen due to industrial constraints. To address this, we propose PAO (Positive-Advantage-Only), a selective RL optimization method. Our analysis reveals that in- discriminate penalization of negative samples (pushing away) in a frozen high-dimensional space disrupts pre-trained semantic man- ifolds. PAO selectively applies gradient updates only to retrieved items with positive advantages, effectively pulling query embed- dings toward high-reward regions while preserving global topo- logical stability. Experiments on both a massive industrial dataset and public benchmarks demonstrate that PAO significantly outper- forms standard RL and distillation baselines.
Shaowei Wei, Chong Huang, Songtao Fang et al.· 0 citations
This work introduces HybridSparse, an end-to-end hybrid retrieval framework that strengthens sparse--dense interaction across modeling, training, and serving and adopts a unified encoder with a shared backbone and jointly optimizes lexical and semantic representations through co-training.
Haotong Bao, Jianjin Zhang, Weihao Han et al.· Annual International ACM SIG...· 0 citations
This work presents DESA (Dense Expansion and Sparse Anchoring), which shares generated references across channels but specializes their integration, which improves nDCG@10 and Recall@20 over the unexpanded query and reduces dense and sparse replay stopping depths.
Externally-transfer performance after distillation remains mixed, so the evidence supports compression of teacher rankings under matched retrieval protocols.
K. Dubovikov, Martin Takác, S. Lahlou· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
