# When to Trust LLMs: Aligning Confidence with Response Quality

arXiv: https://arxiv.org/abs/2404.17287 · HTML: https://mlsanity.com/paper/2404.17287/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 26 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [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)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization](https://mlsanity.com/paper/2210.01241/) (2022)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [Do Language Models Know When They're Hallucinating References?](https://mlsanity.com/paper/2305.18248/) (2023)
- [Alleviating Hallucinations of Large Language Models through Induced Hallucinations](https://mlsanity.com/paper/2312.15710/) (2023)
- [MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space](https://mlsanity.com/paper/2305.12785/) (2023)

## Built on by (most cited first, 30 of 43)

- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Taming Overconfidence in LLMs: Reward Calibration in RLHF](https://mlsanity.com/paper/2410.09724/) (2024)
- [Efficient Test-Time Scaling via Self-Calibration](https://mlsanity.com/paper/2503.00031/) (2025)
- [Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models](https://mlsanity.com/paper/2503.02623/) (2025)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home](https://mlsanity.com/paper/2501.12835/) (2025)
- [Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach](https://mlsanity.com/paper/2505.01997/) (2025)
- [Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization](https://mlsanity.com/paper/2505.15918/) (2025)
- [Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing](https://mlsanity.com/paper/2507.10587/) (2025)
- [CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control](https://mlsanity.com/paper/2405.18727/) (2024)
- [Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling](https://mlsanity.com/paper/2503.02233/) (2025)
- [Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning](https://mlsanity.com/paper/2505.20664/) (2025)
- [Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG](https://mlsanity.com/paper/2511.09980/) (2025)
- [BaseCal: Unsupervised Confidence Calibration via Base Model Signals](https://mlsanity.com/paper/2601.03042/) (2026)
- [BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents](https://mlsanity.com/paper/2510.23458/) (2025)
- [Calibration-Aware Policy Optimization for Reasoning LLMs](https://mlsanity.com/paper/2604.12632/) (2026)
- [Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data](https://mlsanity.com/paper/2504.09895/) (2025)
- [Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation](https://mlsanity.com/paper/2504.14856/) (2025)
- [Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA](https://mlsanity.com/paper/2606.19950/) (2026)
- [Towards Harmonized Uncertainty Estimation for Large Language Models](https://mlsanity.com/paper/2505.19073/) (2025)
- [Judging with Confidence: Calibrating Autoraters to Preference Distributions](https://mlsanity.com/paper/2510.00263/) (2025)
- [Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution](https://mlsanity.com/paper/2511.14275/) (2025)
- [ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models](https://mlsanity.com/paper/2605.12446/) (2026)
- [Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL](https://mlsanity.com/paper/2606.14211/) (2026)
- [When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems](https://mlsanity.com/paper/2410.13029/) (2024)
- [REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models](https://mlsanity.com/paper/2508.14390/) (2025)
- [Linking Perception, Confidence and Accuracy in MLLMs](https://mlsanity.com/paper/2603.12149/) (2026)
- [Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoring](https://mlsanity.com/paper/2605.12398/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Evaluating Consistencies in LLM responses through a Semantic Clustering of Question Answering](https://mlsanity.com/paper/2410.15440/) (2024)

## Abstract (arXiv)

Despite the success of large language models (LLMs) in natural language generation, much evidence shows that LLMs may produce incorrect or nonsensical text. This limitation highlights the importance of discerning when to trust LLMs, especially in safety-critical domains. Existing methods often express reliability by confidence level, however, their effectiveness is limited by the lack of objective guidance. To address this, we propose CONfidence-Quality-ORDer-preserving alignment approach (CONQORD), which leverages reinforcement learning guided by a tailored dual-component reward function. This function integrates quality reward and order-preserving alignment reward functions. Specifically, the order-preserving reward incentivizes the model to verbalize greater confidence for responses of higher quality to align the order of confidence and quality. Experiments demonstrate that CONQORD significantly improves the alignment performance between confidence and response accuracy, without causing over-cautious. Furthermore, the aligned confidence provided by CONQORD informs when to trust LLMs, and acts as a determinant for initiating the retrieval process of external knowledge. Aligning confidence with response quality ensures more transparent and reliable responses, providing better trustworthiness.