mlsanityData to 7 Oct 2026

Uncertainty quantification in fine-tuned LLMs using LoRA ensembles

arXiv 2402.12264 ↗First posted 19 Feb 2024cs.LG cs.AI cs.CLcited by 35

Not on the map. Why?

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.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 67 of its 89 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

67 of 89 references.

References · 67

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  9. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  10. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  11. 2023Mistral 7Bcited by 3,065
  12. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
38 more
  1. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  2. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  3. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  4. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  5. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  6. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  7. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 776
  8. 2022Teaching Models to Express Their Uncertainty in Wordscited by 731
  9. 2023Instruction Tuning with GPT-4cited by 676
  10. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  11. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 658
  12. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  13. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  14. 2015Weight Uncertainty in Neural Networkscited by 554
  15. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  16. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  17. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 438
  18. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
  19. 2018Measuring the Intrinsic Dimension of Objective Landscapescited by 364
  20. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  21. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  22. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
  23. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 209
  24. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
  25. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  26. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  27. 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 179
  28. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  29. 2021Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collectionscited by 128
  30. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  31. 2023Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthinesscited by 121
  32. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  33. 2023Bayesian Low-rank Adaptation for Large Language Modelscited by 112
  34. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  35. 2021Repulsive Deep Ensembles are Bayesiancited by 103
  36. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  37. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  38. 2023LoRA ensembles for large language model fine-tuningcited by 65

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 15; 2026: 11.

35 papers.

Sort:

By area:

  1. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
  2. 2024Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Modelscited by 55
  3. 2024BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Modelscited by 48
  4. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
  5. 2024Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Modelscited by 20
  6. 2025Agentic AI Needs a Systems Theorycited by 19
  7. 2024Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Modelscited by 15
  8. 2025The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguitycited by 15
  9. 2024Training-Free Bayesianization for Low-Rank Adapters of Large Language Modelscited by 10
  10. 2025C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Modelscited by 9
  11. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  12. 2025Estimating LLM Consistency: A User Baseline vs Surrogate Metricscited by 8
23 more
  1. 2025Random-Set Large Language Modelscited by 7
  2. 2024Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMscited by 5
  3. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
  4. 2024Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questionscited by 2
  5. 2025Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysiscited by 2
  6. 2025ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimationcited by 2
  7. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
  8. 2024Uncertainty modeling for fine-tuned implicit functionscited by 1
  9. 2025Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Modelscited by 1
  10. 2025Meta-Learning at Scale for Large Language Models via Low-Rank Amortized Bayesian Meta-Learningcited by 1
  11. 2025The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectivescited by 1
  12. 2026Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuningcited by 1
  13. 2026Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimationcited by 1
  14. 2025Learning Adapter Rank via Symmetry Breakingcited by 0
  15. 2025As If We've Met Before: LLMs Exhibit Certainty in Recognizing Seen Filescited by 0
  16. 2026A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Modelscited by 0
  17. 2026Epistemic Uncertainty for Test-Time Discoverycited by 0
  18. 2026On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inferencecited by 0
  19. 2026iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosiscited by 0
  20. 2026ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentationcited by 0
  21. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Studycited by 0
  22. 2026Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descentcited by 0
  23. 2026Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancingcited by 0