mlsanityData to 7 Oct 2026

DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking

arXiv 2602.00238 ↗First posted 30 Jan 2026cs.CL cs.AI cs.LGcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Existing retrieval-augmented generation (RAG) systems often assume that each query has a single correct answer. This assumption overlooks open-ended information-seeking scenarios where multiple plausible answers are valuable, and where diversity is important for creativity, fairness, and inclusive access to information. We show that standard RAG systems fail to fully use diverse retrieved contexts: simply increasing retrieval diversity does not necessarily lead to diverse generations. To address this limitation, we propose Diverge, a plug-and-play agentic RAG framework that improves the diversity--quality trade-off through iterative, reflection-guided exploration of diverse viewpoints and diversity-aware retrieval support. We further introduce evaluation metrics for characterizing the diversity-quality trade-off in open-ended question answering. Experiments across multiple real-world datasets and backbone LLMs show that Diverge achieves the best trade-off among competitive baselines, increasing diversity by ~2× without noticeable quality degradation. These results reveal a systematic limitation of current RAGs and show the value of explicit diversity modeling.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 51 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

29 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions31 Dec
  2. 2024Evaluation of Retrieval-Augmented Generation: A Survey13 May

Other references · 27

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  5. 2023Understanding the Effects of RLHF on LLM Generalisation and Diversitycited by 386
  6. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  7. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
  8. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 179
  9. 2024Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputscited by 148
  10. 2024ProSA: Assessing and Understanding the Prompt Sensitivity of LLMscited by 145
  11. 2025Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)cited by 137
  12. 2024A Thorough Examination of Decoding Methods in the Era of LLMscited by 112
15 more
  1. 2025Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversitycited by 100
  2. 2025Reasoning with Sampling: Your Base Model is Smarter Than You Thinkcited by 84
  3. 2025Evaluating the Diversity and Quality of LLM Generated Contentcited by 51
  4. 2025Improve LLM-as-a-Judge Ability as a General Abilitycited by 35
  5. 2025IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistancecited by 22
  6. 2021Diversity driven Query Rewriting in Search Advertisingcited by 14
  7. 2025Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMscited by 13
  8. 2024BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedbackcited by 7
  9. 2025Diversity Enhances an LLM's Performance in RAG and Long-context Taskcited by 7
  10. 2022Wikipedia Reader Navigation: When Synthetic Data Is Enoughcited by 6
  11. 2025Logits are All We Need to Adapt Closed Modelscited by 4
  12. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generationcited by 4
  13. 2025Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptationcited by 2
  14. 2025MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answeringcited by 2
  15. 2023Paraphrase Acquisition from Image Captionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Scaling DPPs for RAG: Density Meets Diversity
  2. 2024Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems
  3. 2026Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR Perspective
  4. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  5. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets
  6. 2024Better RAG using Relevant Information Gain
  7. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  8. 2026Finding the Right Balance: Relevance and Diversity in LLM Retrieval