mlsanityData to 14 Oct 2026

SGIC: A Self-Guided Iterative Calibration Framework for RAG

arXiv 2506.16172 ↗First posted 19 Jun 2025cs.CLcited by 8

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

Abstract (arXiv)

Recent research in retrieval-augmented generation (RAG) has concentrated on retrieving useful information from candidate documents. However, numerous methodologies frequently neglect the calibration capabilities of large language models (LLMs), which capitalize on their robust in-context reasoning prowess. This work illustrates that providing LLMs with specific cues substantially improves their calibration efficacy, especially in multi-round calibrations. We present a new SGIC: Self-Guided Iterative Calibration Framework that employs uncertainty scores as a tool. Initially, this framework calculates uncertainty scores to determine both the relevance of each document to the query and the confidence level in the responses produced by the LLMs. Subsequently, it reevaluates these scores iteratively, amalgamating them with prior responses to refine calibration. Furthermore, we introduce an innovative approach for constructing an iterative self-calibration training set, which optimizes LLMs to efficiently harness uncertainty scores for capturing critical information and enhancing response accuracy. Our proposed framework significantly improves performance on both closed-source and open-weight LLMs.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 33 of its 52 references that are in the map. First posted on arXiv 19 Jun 2025.

Builds on

33 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 31

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  9. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  10. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  12. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
19 more
  1. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  3. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 565
  4. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  5. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
  6. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  7. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  8. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  9. 2023RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputscited by 105
  10. 2024Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statementscited by 34
  11. 2024SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflectioncited by 34
  12. 2020TextGAIL: Generative Adversarial Imitation Learning for Text Generationcited by 28
  13. 2019Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarizationcited by 24
  14. 2023Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoningcited by 21
  15. 2022Few-shot Reranking for Multi-hop QA via Language Model Promptingcited by 19
  16. 2023Learning to Simulate Natural Language Feedback for Interactive Semantic Parsingcited by 19
  17. 2021BERTTune: Fine-Tuning Neural Machine Translation with BERTScorecited by 18
  18. 2025Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Modelscited by 13
  19. 2025Not All LoRA Parameters Are Essential: Insights on Inference Necessitycited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systemscited by 6
  2. 2026DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detectioncited by 4
  3. 2026MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessmentcited by 1
  4. 2026From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAGcited by 1
  5. 2025Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translationcited by 0
  6. 2026An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QAcited by 0
  7. 2026Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidencecited by 0
  8. 2026Stochastic Semantic Evidence Graphs: Uncertainty Propagation and Governance for Agentic AIcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation
  2. 2024Retrieval-Augmented Generation with Estimation of Source Reliability
  3. 2025Why Uncertainty Estimation Methods Fall Short in RAG: An Axiomatic Analysis
  4. 2026URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models
  5. 2026BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation
  6. 2025PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation
  7. 2026Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation
  8. 2025Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models