mlsanityData to 7 Oct 2026

Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees

arXiv 2607.14157 ↗First posted 14 Jul 2026cs.LG cs.AI cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

Retrieval over corpora that mix several domains often returns relevant but wrong-domain evidence that ranking metrics miss and that conformal risk control bounds only marginally, under-covering the worst domains. This work introduces C3R, a drop-in control layer that, from an inferred domain posterior and no query-time label, certifies a per-domain contamination budget where feasible and otherwise abstains rather than silently violating; on the hardest domains it guarantees a reduction, not a tight bound. The core is a two-split scheme built on risk-controlling prediction sets, whose finite-sample transfer bound crosses from the inferred to the true domain with fully estimable slack, supports heterogeneous budgets, and inverts for deployment. Population validity rests on this bound and a controlled simulation; across a thousand resampled calibrations the certificate never violates (a stability result) while marginal control violates the most-contaminated domain in every draw, and soft demotion retains more recall than the strongest calibrated cascade at equal certified contamination. The method replicates across open testbeds including an independent one from public federal regulations, and an LLM-judged downstream probe indicates wrong-authority grounding rises with contamination and falls under control. The layer is frozen-stack and reranker-agnostic.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

40 of 57 references.

References · 40

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  6. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  7. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  10. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  11. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  12. 2017Selective Classification for Deep Neural Networkscited by 799
28 more
  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  2. 2016Distribution-Free Predictive Inference For Regressioncited by 657
  3. 2019Passage Re-ranking with BERTcited by 629
  4. 2019Conformalized Quantile Regressioncited by 620
  5. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  6. 2020Fact or Fiction: Verifying Scientific Claimscited by 546
  7. 2019Conformal Prediction Under Covariate Shiftcited by 511
  8. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  9. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  10. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  11. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 426
  12. 2020Classification with Valid and Adaptive Coveragecited by 390
  13. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  14. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 256
  15. 2023LEACE: Perfect linear concept erasure in closed formcited by 254
  16. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  17. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 153
  18. 2023Conformal Prediction With Conditional Guaranteescited by 146
  19. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  20. 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language Modelscited by 27
  21. 2025RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defectscited by 27
  22. 2023Adaptive conformal classification with noisy labelscited by 24
  23. 2022Label Noise Robustness of Conformal Predictioncited by 19
  24. 2024RouterRetriever: Routing over a Mixture of Expert Embedding Modelscited by 12
  25. 2025Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coveragecited by 12
  26. 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Modelscited by 8
  27. 2026Conformal Risk Control for Non-Monotonic Lossescited by 5
  28. 2024Investigating Mixture of Experts in Dense Retrievalcited by 4

Built on by

Not cited yet.