mlsanityData to 14 Oct 2026

Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs

arXiv 2410.06431 ↗First posted 9 Oct 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Accurate uncertainty quantification in large language models (LLMs) is essential for reliable confidence estimation, yet fine-tuned LLMs often become overconfident under limited adaptation data. Existing uncertainty methods for PEFT-based LLMs are largely post hoc, estimating uncertainty after fine-tuning rather than improving how adapters specialize to task-specific input-output relationships. We propose Functional-Level Uncertainty Quantification for Calibrated Fine-Tuning (UQ4CT), which calibrates uncertainty over the functional space induced by prompt-dependent mixtures of LoRA experts. UQ4CT implements this perspective through a mixture-of-experts fine-tuning framework, where a calibration loss aligns functional-level confidence with predictive correctness during training. Across four multiple-choice benchmarks and two open-ended generative QA tasks, UQ4CT reduces Expected Calibration Error (ECE) by over 25% while preserving high accuracy. Under distribution shift, UQ4CT maintains superior calibration and competitive accuracy, demonstrating improved reliability and generalization for fine-tuned LLMs.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 82 of its 99 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

82 of 99 references.

References · 82

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2022Training language models to follow instructions with human feedbackcited by 15,971
  5. 2024The Llama 3 Herd of Modelscited by 14,715
  6. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  8. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  9. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  10. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  11. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  12. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
38 more
  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2023Mistral 7Bcited by 3,164
  7. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  9. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  10. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  11. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  12. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  13. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  14. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  15. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  16. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  17. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  18. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  19. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  20. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  21. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,121
  22. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  23. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  24. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  25. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 819
  26. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  27. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 758
  28. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  29. 2023Instruction Tuning with GPT-4cited by 686
  30. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 650
  31. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  32. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  33. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  34. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 324
  35. 2023VeRA: Vector-based Random Matrix Adaptationcited by 300
  36. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
  37. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 236
  38. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 221

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 5.

6 papers.

  1. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 121
  2. 2026Spend Experts Where You Are Unsure: Confidence-Adaptive Routing for Mixture-of-Experts LoRAcited by 2
  3. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
  4. 2026Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimationcited by 1
  5. 2026READY or Not: Reliable Enterprise Agent Deploymentcited by 0
  6. 2026DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Revisiting Uncertainty Estimation and Calibration of Large Language Models
  2. 2026Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
  3. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey
  4. 2025Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification
  5. 2026Uncertainty Quantification for LLM Function-Calling
  6. 2026Rethinking Uncertainty Evaluation in Large Language Models
  7. 2025Can Linear Probes Measure LLM Uncertainty?
  8. 2025Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding