mlsanityData to 14 Oct 2026

Retrieval-Augmented Linguistic Calibration

arXiv 2605.19344 ↗First posted 19 May 2026cs.CLcited by 2

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

Abstract (arXiv)

Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic confidence expressions remains underexplored. In particular, co-occurring linguistic cues, contextual variation, and subjective audience interpretation pose unique challenges. We therefore model linguistic confidence as a distribution over plausible perceived probability values that a statement is correct, capturing interpretation variability that scalar representations discard. Within this distributional framework, we introduce faithfulness as a complementary evaluation dimension and present Faithfulness Divergence (FD), an information-theoretic metric quantifying the surprise induced in audience beliefs upon truth revelation. Building on these foundations, we present Retrieval-Augmented Linguistic Calibration (RALC), a lightweight post-hoc pipeline that propagates calibrated confidence signals back into natural language via retrieval-augmented rewriting. Across three QA benchmarks and five LLM families, RALC improves in-domain faithfulness and calibration up to 66% and 58%, respectively, outperforming black-box and grey-box calibration baselines.

Key facts. Cited by 2 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 24 of its 39 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

24 of 39 references.

References · 24

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2017On Calibration of Modern Neural Networkscited by 4,960
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  7. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  8. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  9. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  10. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  11. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  12. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 150
12 more
  1. 2024What Large Language Models Know and What People Think They Knowcited by 110
  2. 2019Distribution Calibration for Regressioncited by 89
  3. 2024Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?cited by 87
  4. 2023On the Calibration of Large Language Models and Alignmentcited by 73
  5. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  6. 2024Calibrating Long-form Generations from Large Language Modelscited by 32
  7. 2025Revisiting Uncertainty Estimation and Calibration of Large Language Modelscited by 23
  8. 2023Calibration by Distribution Matching: Trainable Kernel Calibration Metricscited by 20
  9. 2024Calibrating Expressions of Certaintycited by 7
  10. 2025Can Large Language Models Express Uncertainty Like Human?cited by 5
  11. 2025An Entropic Metric for Measuring Calibration of Machine Learning Modelscited by 2
  12. 2026Extending confidence calibration to generalised measures of variationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Studycited by 0
  2. 2026On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Identifying Influential N-grams in Confidence Calibration via Regression Analysis
  2. 2026Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models
  3. 2026Quantifying Faithful Confidence Expression in Large Reasoning Models
  4. 2026An Analysis of Training-Free Self-Reported Confidence in Language Models
  5. 2026Rethinking Uncertainty Evaluation in Large Language Models
  6. 2026Closing the Confidence-Faithfulness Gap in Large Language Models
  7. 2025Calibrating Verbalized Confidence with Self-Generated Distractors
  8. 2026FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness