Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction

• URL: http://arxiv.org/abs/2511.17908v1
• Date: Sat, 22 Nov 2025 04:17:06 GMT
• Title: Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction
• Authors: Debashish Chakraborty, Eugene Yang, Daniel Khashabi, Dawn Lawrie, Kevin Duh,
• Abstract summary: Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models.<n>Existing pre-generation filters rely on confidence scores, offering no statistical control over retained evidence.<n>We demonstrate context engineering through conformal prediction, a coverage-controlled filtering framework.
• Score: 40.28465841863481
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models (LLMs) by incorporating retrieved evidence, but LLM accuracy declines when long or noisy contexts exceed the model's effective attention span. Existing pre-generation filters rely on heuristics or uncalibrated LLM confidence scores, offering no statistical control over retained evidence. We evaluate and demonstrate context engineering through conformal prediction, a coverage-controlled filtering framework that removes irrelevant content while preserving recall of supporting evidence. Using both embedding- and LLM-based scoring functions, we test this approach on the NeuCLIR and RAGTIME collections. Conformal filtering consistently meets its target coverage, ensuring that a specified fraction of relevant snippets are retained, and reduces retained context by 2-3x relative to unfiltered retrieval. On NeuCLIR, downstream factual accuracy measured by ARGUE F1 improves under strict filtering and remains stable at moderate coverage, indicating that most discarded material is redundant or irrelevant. These results demonstrate that conformal prediction enables reliable, coverage-controlled context reduction in RAG, offering a model-agnostic and principled approach to context engineering.

Related papers

• Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling [42.10910149675583]
  Real-world degradations make correspondences between low-quality (LQ) inputs and reference (Ref) images unreliable.<n>We propose Ada-RefSR, a single-step diffusion framework guided by a "Trust but verify" principle.<n>Experiments on multiple datasets demonstrate that Ada-RefSR achieves a strong balance of fidelity, naturalness, and efficiency.
  arXiv  Detail & Related papers  (2026-02-02T09:34:57Z)
• Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses [18.60553322553765]
  We reformulate conformal inference in a multiplicative filtering setting, modeling factuality as a product of claim-level scores.<n>Our method, Multi-LLM Adaptive Conformal Inference (MACI), leverages ensembles to produce more accurate factuality-scores.<n>Experiments show that MACI consistently achieves user-specified coverage with substantially higher retention and lower time cost than baselines.
  arXiv  Detail & Related papers  (2026-02-01T15:34:45Z)
• NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems [53.52419750390942]
  Large language models (LLMs) are used in mission-critical factual domains.<n>LLMs exhibit poor calibration performance due to noisy retrieved contexts.<n>We propose NAACL Rules (Noise-AwAre Confidence CaLibration Rules) to provide a principled foundation for resolving overconfidence under noise.
  arXiv  Detail & Related papers  (2026-01-16T05:38:25Z)
• RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence [18.268335797537983]
  Retrieval-Augmented Generation (RAG) is a technique to enhance factual accuracy by integrating external knowledge into the generation process.<n>This paper introduces Radiant, a framework that merges RAG with alignment designed to optimize the interplay between retrieved evidence and generated content.
  arXiv  Detail & Related papers  (2025-06-28T21:40:35Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Robust Conformal Outlier Detection under Contaminated Reference Data [20.864605211132663]
  Conformal prediction is a flexible framework for calibrating machine learning predictions.<n>In outlier detection, this calibration relies on a reference set of labeled inlier data to control the type-I error rate.<n>This paper analyzes the impact of contamination on the validity of conformal methods.
  arXiv  Detail & Related papers  (2025-02-07T10:23:25Z)
• Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output [49.893971654861424]
  We present a light-weight approach for detecting nonfactual outputs from retrieval-augmented generation (RAG) We compute a factuality score that can be thresholded to yield a binary decision. Our experiments show high area under the ROC curve (AUC) across a wide range of relevant open source datasets.
  arXiv  Detail & Related papers  (2024-11-01T20:44:59Z)
• ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems [2.8692611791027893]
  Retrieval-Augmented Generation (RAG) systems generate inaccurate responses due to the retrieval of irrelevant or loosely related information.<n>We propose ChunkRAG, a framework that enhances RAG systems by evaluating and filtering retrieved information at the chunk level.
  arXiv  Detail & Related papers  (2024-10-25T14:07:53Z)
• AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation [57.8363998797433]
  We propose AMRFact, a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs) Our approach parses factually consistent summaries into AMR graphs and injects controlled factual inconsistencies to create negative examples, allowing for coherent factually inconsistent summaries to be generated with high error-type coverage.
  arXiv  Detail & Related papers  (2023-11-16T02:56:29Z)
• Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning [57.88785630755165]
  Empirical risk minimization (ERM) is the workhorse of machine learning, but its model-agnostic guarantees can fail when we use adaptively collected data. We study a generic importance sampling weighted ERM algorithm for using adaptively collected data to minimize the average of a loss function over a hypothesis class. For policy learning, we provide rate-optimal regret guarantees that close an open gap in the existing literature whenever exploration decays to zero.
  arXiv  Detail & Related papers  (2021-06-03T09:50:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.