# Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting

arXiv: https://arxiv.org/abs/2310.11732 · HTML: https://mlsanity.com/paper/2310.11732/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 18 Oct 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (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)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (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)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts](https://mlsanity.com/paper/2202.01279/) (2022)
- [Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning](https://mlsanity.com/paper/2010.15875/) (2020)
- [Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning](https://mlsanity.com/paper/2003.07329/) (2020)
- [Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla](https://mlsanity.com/paper/2307.09458/) (2023)
- [DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales](https://mlsanity.com/paper/2308.01320/) (2023)

## Built on by (most cited first, 20 of 20)

- [Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration](https://mlsanity.com/paper/2402.00367/) (2024)
- [Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations](https://mlsanity.com/paper/2404.10960/) (2024)
- [Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations](https://mlsanity.com/paper/2502.07068/) (2025)
- [Calibrating the Confidence of Large Language Models by Eliciting Fidelity](https://mlsanity.com/paper/2404.02655/) (2024)
- [Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models](https://mlsanity.com/paper/2412.14660/) (2024)
- [Intelligent AI Delegation](https://mlsanity.com/paper/2602.11865/) (2026)
- [Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A](https://mlsanity.com/paper/2402.13213/) (2024)
- [Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation](https://mlsanity.com/paper/2406.01806/) (2024)
- [Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models](https://mlsanity.com/paper/2405.10025/) (2024)
- [Teaching LLMs to Abstain across Languages via Multilingual Feedback](https://mlsanity.com/paper/2406.15948/) (2024)
- [Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models](https://mlsanity.com/paper/2407.11282/) (2024)
- [AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment](https://mlsanity.com/paper/2506.04089/) (2025)
- [Unified Active Retrieval for Retrieval Augmented Generation](https://mlsanity.com/paper/2406.12534/) (2024)
- [BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence](https://mlsanity.com/paper/2604.03216/) (2026)
- [Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration](https://mlsanity.com/paper/2409.03225/) (2024)
- [Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs](https://mlsanity.com/paper/2604.01457/) (2026)
- [A Survey of LLM Alignment: Instruction Understanding, Intention Reasoning, and Reliable Generation](https://mlsanity.com/paper/2502.09101/) (2025)
- [Don't Blink: Evidence Collapse during Multimodal Reasoning](https://mlsanity.com/paper/2604.04207/) (2026)
- [Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration](https://mlsanity.com/paper/2608.07419/) (2026)
- [Jailbreaks for Black-Box Uncertainty Quantification in Large Reasoning Models](https://mlsanity.com/paper/2609.35350/) (2026)

## Abstract (arXiv)

Despite the significant progress made in practical applications of aligned language models (LMs), they tend to be overconfident in output answers compared to the corresponding pre-trained LMs. In this work, we systematically evaluate the impact of the alignment process on logit-based uncertainty calibration of LMs under the multiple-choice setting. We first conduct a thoughtful empirical study on how aligned LMs differ in calibration from their pre-trained counterparts. Experimental results reveal that there are two distinct uncertainties in LMs under the multiple-choice setting, which are responsible for the answer decision and the format preference of the LMs, respectively. Then, we investigate the role of these two uncertainties on aligned LM's calibration through fine-tuning in simple synthetic alignment schemes and conclude that one reason for aligned LMs' overconfidence is the conflation of these two types of uncertainty. Furthermore, we examine the utility of common post-hoc calibration methods for aligned LMs and propose an easy-to-implement and sample-efficient method to calibrate aligned LMs. We hope our findings could provide insights into the design of more reliable alignment processes for LMs.