# Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation

arXiv: https://arxiv.org/abs/2311.08877 · HTML: https://mlsanity.com/paper/2311.08877/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [Selective Classification Can Magnify Disparities Across Groups](https://mlsanity.com/paper/2010.14134/) (2020)
- [Binary Classifier Calibration: Non-parametric approach](https://mlsanity.com/paper/1401.3390/) (2014)
- [Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings](https://mlsanity.com/paper/1606.06368/) (2016)

## Built on by (most cited first, 30 of 39)

- [Language Model Cascades: Token-level uncertainty and beyond](https://mlsanity.com/paper/2404.10136/) (2024)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation](https://mlsanity.com/paper/2402.09267/) (2024)
- [Reasoning Models Better Express Their Confidence](https://mlsanity.com/paper/2505.14489/) (2025)
- [A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice](https://mlsanity.com/paper/2410.15326/) (2024)
- [Incoherent Probability Judgments in Large Language Models](https://mlsanity.com/paper/2401.16646/) (2024)
- [Cycles of Thought: Measuring LLM Confidence through Stable Explanations](https://mlsanity.com/paper/2406.03441/) (2024)
- [Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs](https://mlsanity.com/paper/2406.11514/) (2024)
- [MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs](https://mlsanity.com/paper/2505.24858/) (2025)
- [Perceptions of Linguistic Uncertainty by Language Models and Humans](https://mlsanity.com/paper/2407.15814/) (2024)
- [The challenge of uncertainty quantification of large language models in medicine](https://mlsanity.com/paper/2504.05278/) (2025)
- [Conformal Language Model Reasoning with Coherent Factuality](https://mlsanity.com/paper/2505.17126/) (2025)
- [Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?](https://mlsanity.com/paper/2408.14141/) (2024)
- [Gatekeeper: Improving Model Cascades Through Confidence Tuning](https://mlsanity.com/paper/2502.19335/) (2025)
- [Collaborative Performance Prediction for Large Language Models](https://mlsanity.com/paper/2407.01300/) (2024)
- [A Survey of Calibration Process for Black-Box LLMs](https://mlsanity.com/paper/2412.12767/) (2024)
- [Epistemic Integrity in Large Language Models](https://mlsanity.com/paper/2411.06528/) (2024)
- [Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models](https://mlsanity.com/paper/2504.02902/) (2025)
- [Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.13692/) (2024)
- [Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration](https://mlsanity.com/paper/2409.03225/) (2024)
- [Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns](https://mlsanity.com/paper/2509.24988/) (2025)
- [Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models](https://mlsanity.com/paper/2402.11279/) (2024)
- [Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review](https://mlsanity.com/paper/2504.18346/) (2025)
- [Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs](https://mlsanity.com/paper/2606.32032/) (2026)
- [Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes](https://mlsanity.com/paper/2506.01512/) (2025)
- [Confidence Estimation for Text-to-SQL in Large Language Models](https://mlsanity.com/paper/2508.14056/) (2025)
- [Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA](https://mlsanity.com/paper/2602.00279/) (2026)
- [Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring](https://mlsanity.com/paper/2507.17442/) (2025)
- [Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation](https://mlsanity.com/paper/2510.13750/) (2025)
- [SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models](https://mlsanity.com/paper/2510.13836/) (2025)

## Abstract (arXiv)

To maintain user trust, large language models (LLMs) should signal low confidence on examples where they are incorrect, instead of misleading the user. The standard approach of estimating confidence is to use the softmax probabilities of these models, but as of November 2023, state-of-the-art LLMs such as GPT-4 and Claude-v1.3 do not provide access to these probabilities. We first study eliciting confidence linguistically -- asking an LLM for its confidence in its answer -- which performs reasonably (80.5% AUC on GPT-4 averaged across 12 question-answering datasets -- 7% above a random baseline) but leaves room for improvement. We then explore using a surrogate confidence model -- using a model where we do have probabilities to evaluate the original model's confidence in a given question. Surprisingly, even though these probabilities come from a different and often weaker model, this method leads to higher AUC than linguistic confidences on 9 out of 12 datasets. Our best method composing linguistic confidences and surrogate model probabilities gives state-of-the-art confidence estimates on all 12 datasets (84.6% average AUC on GPT-4).