mlsanityData to 7 Oct 2026

Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation

arXiv 2609.38222 ↗First posted 27 Sep 2026cs.CL cs.LG stat.MLcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated claims are factually supported. This problem is especially relevant in multi-hop RAG, where retrieval and reasoning proceed through multiple dependent stages. We study whether claim-level conformal factuality control, previously developed for RAG, remains effective in this setting. We apply split-conformal claim filtering to multi-hop RAG and evaluate it on HotpotQA, Natural Questions, and TriviaQA using Llama 3.1 8B and GPT-4o-mini, together with a single-hop reference experiment. Across all six multi-hop model-dataset configurations, increasingly stringent conformal targets consistently increase the fraction of responses whose retained claims are fully supported. At the 95% target, this rate ranges from 95.80% to 97.20%, compared with 55.60%-76.03% without filtering. However, the improvement is strongly selective: only 4.41%-31.09% of generated claims are retained and 9.70%-51.40% of responses remain non-empty at the 95% target. These results show that conformal factuality extends to multi-hop RAG, while demonstrating that nominal reliability must be interpreted jointly with claim retention and abstention.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 14 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

13 of 14 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights17 Mar
  2. 2025Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality26 Jun
  3. 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models5 Feb

Other references · 10

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  6. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  7. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  8. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
  9. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 253
  10. 2024Language Models with Conformal Factuality Guaranteescited by 128

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies
  2. 2026When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
  3. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
  4. 2025Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction
  5. 2025Investigating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries
  6. 2026Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
  7. 2026CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency
  8. 2024BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression