paper-with-me

Papers

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

2024-10-09 · Ruijia Niu, Dongxia Wu, Rose Yu, Yi-An Ma

Accurate uncertainty quantification of large language models (LLMs) provides credibility measure over their outputs. However, fine-tuned LLMs often struggle with overconfidence in uncertain predictions due to the limitations in the models' ability to generalize with limited data. Existing parameter efficient fine-tuning (PEFT) uncertainty quantification methods for LLMs focus on post fine-tuning stage and fall short of calibrating epistemic uncertainty. To address these limitations, we propose Functional-Level Uncertainty Quantification for Calibrated Fine-Tuning (UQ4CT), which captures and calibrates epistemic uncertainty over the space of functions that map input prompts to outputs. We implement UQ4CT during the fine-tuning stage via a mixture-of-experts framework that hierarchically decomposes the functional space. We demonstrate that UQ4CT reduces Expected Calibration Error (ECE) by more than $25\%$ while maintaining high accuracy across $5$ benchmarks. Even under distribution shift, UQ4CT maintains superior ECE performance with high accuracy, showcasing improved generalizability.

📄 PDF Abstract BibTeX arXiv:2410.06431

Code (0)

등록된 구현이 없습니다.

Tasks

Common Sense ReasoningMixture-of-Expertsparameter-efficient fine-tuningUncertainty Quantification

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Calibrated Uncertainty Quantification for Operator Learning via Conformal Prediction

2024-02-02 · Ziqi Ma, Kamyar Azizzadenesheli, Anima Anandkumar

Operator learning has been increasingly adopted in scientific and engineering applications, many of which require calibrated uncertainty quantification. Since the output of operator learning is a continuous function, qua…

Conformal PredictionOperator learningPredictionUncertainty Quantification

A Physics inspired Functional Operator for Model Uncertainty Quantification in the RKHS

2021-09-22 · Rishabh Singh, Jose C. Principe

Accurate uncertainty quantification of model predictions is a crucial problem in machine learning. Existing Bayesian methods, being highly iterative, are expensive to implement and often fail to accurately capture a mode…

Uncertainty Quantification

Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models

2024-10-28 · Tuwe Löfström, Fatima Rabia Yapicioglu, Alessandra Stramiglio, Helena Löfström 외

This paper introduces Fast Calibrated Explanations, a method designed for generating rapid, uncertainty-aware explanations for machine learning models. By incorporating perturbation techniques from ConformaSight - a glob…

Computational EfficiencyFeature ImportanceregressionUncertainty Quantification

Concentration and Calibration in Predictive Bayesian Inference

2026-05-01 · David T. Frazier, Hui Wang arxiv

Predictive Bayesian inference (PBI) represents a model-and prior-agnostic approach to standard Bayesian inference which allows users to quantify uncertainty for a functional of interest only by specifying a forward predi…

Bayesian Inference

When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting

2021-06-07 · NeurIPS 2021 12 · Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez, Chao Zhang 외

Accurate and trustworthy epidemic forecasting is an important problem that has impact on public health planning and disease mitigation. Most existing epidemic forecasting models disregard uncertainty quantification, resu…

Time SeriesTime Series AnalysisTime Series ForecastingUncertainty Quantification