mlsanityData to 14 Oct 2026

Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection

arXiv 2601.17532 ↗First posted 24 Jan 2026cs.CL cs.AIcited by 3

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Retrieval-augmented generation (RAG) grounds large language models with external evidence, but under a limited context budget, the key challenge is deciding which retrieved passages should be injected. We show that retrieval relevance metrics (e.g., NDCG) correlate weakly with end-to-end QA quality and can even become negatively correlated under multi-passage injection, where redundancy and mild conflicts destabilize generation. We propose Information Gain Pruning (IGP), a deployment-friendly reranking-and-pruning module that selects evidence using a generator-aligned utility signal and filters weak or harmful passages before truncation, without changing existing budget interfaces. Across five open-domain QA benchmarks and multiple retrievers and generators, IGP consistently improves the quality--cost trade-off. In a representative multi-evidence setting, IGP delivers about +12--20% relative improvement in average F1 while reducing final-stage input tokens by roughly 76--79% compared to retriever-only baselines.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 32 of its 39 references that are in the map. First posted on arXiv 24 Jan 2026.

Builds on

32 of 39 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs2 Jul
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories20 Dec
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Training10 Feb

Other references · 28

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  9. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  10. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  11. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  12. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
16 more
  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  2. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  4. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
  5. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  6. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  7. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  8. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 121
  9. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 119
  10. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generationcited by 93
  11. 2023Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labelscited by 86
  12. 2024Bridging the Preference Gap between Retrievers and LLMscited by 69
  13. 2025Retrieval-Augmented Generation with Conflicting Evidencecited by 63
  14. 2025Hierarchical Document Refinement for Long-context Retrieval-augmented Generationcited by 16
  15. 2025GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesiscited by 12
  16. 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026How Many Tools Should an LLM Agent See? A Chance-Corrected Answercited by 7
  2. 2026CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generationcited by 1
  3. 2026LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passagescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
  2. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  3. 2026OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation
  4. 2026PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation
  5. 2025Aligning Extraction and Generation for Robust Retrieval-Augmented Generation
  6. 2026Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting
  7. 2026Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach
  8. 2025InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering