paper-with-me

Papers

Streamlining Conformal Information Retrieval via Score Refinement

2024-10-03 · Yotam Intrator, Ori Kelner, Regev Cohen, Roman Goldenberg, Ehud Rivlin, Daniel Freedman

Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant information, yet existing approaches produce large-sized sets, incurring high computational costs and slow response times. In this work, we introduce a score refinement method that applies a simple monotone transformation to retrieval scores, leading to significantly smaller conformal sets while maintaining their statistical guarantees. Experiments on various BEIR benchmarks validate the effectiveness of our approach in producing compact sets containing relevant information.

📄 PDF Abstract BibTeX arXiv:2410.02914

Code (0)

등록된 구현이 없습니다.

Tasks

Conformal PredictionInformation RetrievalRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Multivariate Standardized Residuals for Conformal Prediction

2025-07-28 · Sacha Braun, Eugène Berta, Michael I. Jordan, Francis Bach arxiv

While split conformal prediction guarantees marginal coverage, approaching the stronger property of conditional coverage is essential for reliable uncertainty quantification. Naive conformal scores, however, suffer from …

CONFLARE: CONFormal LArge language model REtrieval

2024-04-04 · Pouria Rouzrokh, Shahriar Faghani, Cooper U. Gamble, Moein Shariatnia 외

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hall…

Conformal PredictionLanguage ModelingLanguage ModellingLarge Language Model+5

ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift

2026-06-16 · Jeffery Opoku, David Banahene arxiv

Modern AI agents retrieve documents, call tools, check intermediate information, and then produce a final answer or action. This creates a risk-control problem that is not visible from the final answer alone. A final res…

RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction

2026-05-09 · Manuel Heurich, Maximilian Granz, Tim Landgraf arxiv

Recent advances in uncertainty quantification for time series forecasting show that conformal prediction can provide reliable prediction intervals, yet standard conformal methods are often inefficient under temporal depe…

Time Series ForecastingTime Series Prediction

Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality

2025-06-26 · Naihe Feng, Yi Sui, Shiyi Hou, Jesse C. Cresswell 외

Existing research on Retrieval-Augmented Generation (RAG) primarily focuses on improving overall question-answering accuracy, often overlooking the quality of sub-claims within generated responses. Recent methods that at…

Conformal PredictionQuestion AnsweringRAGRetrieval+1