Finding the Right Balance: Relevance and Diversity in LLM Retrieval

cs.IR, cs.CL

Submitted: 2026-10-07

Updated: 2026-10-07

Comments: 36 pages, 8 figures, 13 tables. Code and results: https://github.com/GuillaumeBrouillette/finding-the-right-balance

Code: https://github.com/GuillaumeBrouillette/finding-the-right-balance

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

Sources

• From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents
• Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• ARAGOG: Advanced RAG Output Grading
• DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking
• SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval
• Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming
• From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented Generation
• Passage Re-ranking with BERT
• AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG
• Better RAG using Relevant Information Gain
• Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs
• Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks
• Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
• Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
• Retriever Portfolios: A Principled Approach to Adaptive RAG
• Scaling DPPs for RAG: Density Meets Diversity
• Diversity Enhances an LLM's Performance in RAG and Long-context Task
• Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications
• Corrective Retrieval Augmented Generation

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
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
• Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition