Robustness of IR Models to Collection Growth

arXiv:2608.23419 · cs.IR, cs.CL · Submitted 2026-08-24 · Read on arXiv

cs.IR, cs.CL

Submitted: 2026-08-24

Updated: 2026-08-25

Terminology

• Collection Growth — 29× in this paper
• Information Retrieval — 27× in this paper
• Robustness — 21× in this paper · explained in 5 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Contextual Document Embeddings — 2× in this paper
• Pseudo Relevance Feedback — 2× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Collection Precision — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Cross Encoders — 1× in this paper
• Distillation — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• National Institute of Standards and Technology — 1× in this paper
• RAG — 1× in this paper · explained in 3 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Overview of the TREC 2019 deep learning track
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
• Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective
• The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models
• RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
• UMBRELA: UMbrela is the (Open-Source Reproduction of the) Bing RELevance Assessor
• CORD-19: The COVID-19 Open Research Dataset

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