# Uncertainty quantification in fine-tuned LLMs using LoRA ensembles

arXiv: https://arxiv.org/abs/2402.12264 · HTML: https://mlsanity.com/paper/2402.12264/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 89 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Builds on (most cited first, 30 of 67)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [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)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Bayesian Deep Learning and a Probabilistic Perspective of Generalization](https://mlsanity.com/paper/2002.08791/) (2020)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)

## Built on by (most cited first, 30 of 37)

- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models](https://mlsanity.com/paper/2407.16221/) (2024)
- [BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models](https://mlsanity.com/paper/2406.11675/) (2024)
- [TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning](https://mlsanity.com/paper/2505.11737/) (2025)
- [Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2405.03425/) (2024)
- [Agentic AI Needs a Systems Theory](https://mlsanity.com/paper/2503.00237/) (2025)
- [The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity](https://mlsanity.com/paper/2511.04418/) (2025)
- [Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models](https://mlsanity.com/paper/2409.02976/) (2024)
- [Training-Free Bayesianization for Low-Rank Adapters of Large Language Models](https://mlsanity.com/paper/2412.05723/) (2024)
- [C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2505.17773/) (2025)
- [Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'](https://mlsanity.com/paper/2505.04950/) (2025)
- [Estimating LLM Consistency: A User Baseline vs Surrogate Metrics](https://mlsanity.com/paper/2505.23799/) (2025)
- [Random-Set Large Language Models](https://mlsanity.com/paper/2504.18085/) (2025)
- [Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs](https://mlsanity.com/paper/2410.06431/) (2024)
- [Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review](https://mlsanity.com/paper/2504.18346/) (2025)
- [Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questions](https://mlsanity.com/paper/2406.10999/) (2024)
- [Uncertainty modeling for fine-tuned implicit functions](https://mlsanity.com/paper/2406.12082/) (2024)
- [Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysis](https://mlsanity.com/paper/2502.06173/) (2025)
- [ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation](https://mlsanity.com/paper/2506.01116/) (2025)
- [The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives](https://mlsanity.com/paper/2510.06096/) (2025)
- [The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models](https://mlsanity.com/paper/2606.22792/) (2026)
- [Credal Large Language Models for Semantic Commitment under Uncertainty](https://mlsanity.com/paper/2608.23244/) (2026)
- [Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2505.11731/) (2025)
- [Learning Adapter Rank via Symmetry Breaking](https://mlsanity.com/paper/2506.22809/) (2025)
- [Meta-Learning at Scale for Large Language Models via Low-Rank Amortized Bayesian Meta-Learning](https://mlsanity.com/paper/2508.14285/) (2025)
- [Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning](https://mlsanity.com/paper/2601.13697/) (2026)
- [Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation](https://mlsanity.com/paper/2607.02182/) (2026)
- [As If We've Met Before: LLMs Exhibit Certainty in Recognizing Seen Files](https://mlsanity.com/paper/2511.15192/) (2025)
- [A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models](https://mlsanity.com/paper/2603.26363/) (2026)
- [Epistemic Uncertainty for Test-Time Discovery](https://mlsanity.com/paper/2605.11328/) (2026)

## Abstract (arXiv)

Fine-tuning large language models can improve task specific performance, although a general understanding of what the fine-tuned model has learned, forgotten and how to trust its predictions is still missing. We derive principled uncertainty quantification for fine-tuned LLMs with posterior approximations using computationally efficient low-rank adaptation ensembles. We analyze three common multiple-choice datasets using low-rank adaptation ensembles based on Mistral-7b, and draw quantitative and qualitative conclusions on their perceived complexity and balance between retained prior knowledge and domain specific adaptation during and after fine-tuning. We identify unexpected retention of acquired knowledge during fine-tuning in the overfitting regime.