mlsanityData to 7 Oct 2026

SUGAR: Leveraging Contextual Confidence for Smarter Retrieval

arXiv 2501.04899 ↗First posted 9 Jan 2025cs.CL cs.AIcited by 6

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

Abstract (arXiv)

Bearing in mind the limited parametric knowledge of Large Language Models (LLMs), retrieval-augmented generation (RAG) which supplies them with the relevant external knowledge has served as an approach to mitigate the issue of hallucinations to a certain extent. However, uniformly retrieving supporting context makes response generation source-inefficient, as triggering the retriever is not always necessary, or even inaccurate, when a model gets distracted by noisy retrieved content and produces an unhelpful answer. Motivated by these issues, we introduce Semantic Uncertainty Guided Adaptive Retrieval (SUGAR), where we leverage context-based entropy to actively decide whether to retrieve and to further determine between single-step and multi-step retrieval. Our empirical results show that selective retrieval guided by semantic uncertainty estimation improves the performance across diverse question answering tasks, as well as achieves a more efficient inference.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 31 of its 38 references that are in the map. First posted on arXiv 9 Jan 2025.

Builds on

31 of 38 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries18 Jun
  2. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence16 Apr
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  5. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise2 May

Other references · 26

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  12. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
14 more
  1. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  4. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  5. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  6. 2023Active Retrieval Augmented Generationcited by 506
  7. 2024Large Language Models: A Surveycited by 506
  8. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  9. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 176
  10. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
  11. 2023Adaptation with Self-Evaluation to Improve Selective Prediction in LLMscited by 49
  12. 2023Interpretable Unified Language Checkingcited by 26
  13. 2024Evaluating the External and Parametric Knowledge Fusion of Large Language Modelscited by 9
  14. 2023The Web Can Be Your Oyster for Improving Large Language Modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generationcited by 9
  2. 2025Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAGcited by 5
  3. 2026The Anatomy of Uncertainty in LLMscited by 2
  4. 2026SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Searchcited by 2
  5. 2026Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Predictioncited by 1
  6. 2026Hybrid Adversarial Defence for Natural Language Understanding Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
  2. 2026Interpretable Uncertainty for Adaptive Retrieval and Reasoning in Question Answering
  3. 2025QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation
  4. 2026URAG: A Benchmark for Uncertainty Quantification in Retrieval-Augmented Large Language Models
  5. 2026Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language Models
  6. 2025To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation
  7. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  8. 2026Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs