Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors

arXiv:2608.15851 · cs.IR, cs.CL · Submitted 2026-08-16 · Read on arXiv

cs.IR, cs.CL

Submitted: 2026-08-16

Updated: 2026-08-31

Comments: 12 pages, 4 figures. Code and artifacts: https://github.com/ln-one/dense-expands-sparse-anchors

Code: https://github.com/ln-one/dense-expands-sparse-anchors

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Robustness — 6× in this paper · explained in 5 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Additivity — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Dense Expansion and Sparse Anchoring — 1× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Query Expansion by Prompting Large Language Models
• Mistral 7B
• Exact Adaptive Hybrid Retrieval Without Fixed Top-L Cutoffs
• Qwen2.5 Technical Report

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
• Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
• UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG