Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach

• URL: http://arxiv.org/abs/2404.15993v4
• Date: Wed, 23 Oct 2024 08:33:54 GMT
• Title: Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach
• Authors: Linyu Liu, Yu Pan, Xiaocheng Li, Guanting Chen,
• Abstract summary: We study the problem of uncertainty estimation and calibration for LLMs. We propose a supervised approach that leverages labeled datasets to estimate the uncertainty in LLMs' responses. Our method is easy to implement and adaptable to different levels of model accessibility including black box, grey box, and white box.
• Score: 6.209293868095268
• License:
• Abstract: In this paper, we study the problem of uncertainty estimation and calibration for LLMs. We begin by formulating the uncertainty estimation problem, a relevant yet underexplored area in existing literature. We then propose a supervised approach that leverages labeled datasets to estimate the uncertainty in LLMs' responses. Based on the formulation, we illustrate the difference between the uncertainty estimation for LLMs and that for standard ML models and explain why the hidden neurons of the LLMs may contain uncertainty information. Our designed approach demonstrates the benefits of utilizing hidden activations to enhance uncertainty estimation across various tasks and shows robust transferability in out-of-distribution settings. We distinguish the uncertainty estimation task from the uncertainty calibration task and show that better uncertainty estimation leads to better calibration performance. Furthermore, our method is easy to implement and adaptable to different levels of model accessibility including black box, grey box, and white box.

Related papers

• Uncertainty Quantification in Stereo Matching [61.73532883992135]
  We propose a new framework for stereo matching and its uncertainty quantification. We adopt Bayes risk as a measure of uncertainty and estimate data and model uncertainty separately. We apply our uncertainty method to improve prediction accuracy by selecting data points with small uncertainties.
  arXiv  Detail & Related papers  (2024-12-24T23:28:20Z)
• SAUP: Situation Awareness Uncertainty Propagation on LLM Agent [52.444674213316574]
  Large language models (LLMs) integrated into multistep agent systems enable complex decision-making processes across various applications. Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multistep decision-making process and the dynamic interactions between agents and their environments. We propose SAUP, a novel framework that propagates uncertainty through each step of an LLM-based agent's reasoning process.
  arXiv  Detail & Related papers  (2024-12-02T01:31:13Z)
• A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice [7.687545159131024]
  We clarify the definitions of uncertainty and confidence, highlighting their distinctions and implications for model predictions. We categorize various classes of uncertainty estimation methods derived from approaches. We also explore techniques for uncertainty into diverse applications, including out-of-distribution detection, data annotation, and question clarification.
  arXiv  Detail & Related papers  (2024-10-20T07:55:44Z)
• Black-box Uncertainty Quantification Method for LLM-as-a-Judge [13.45579129351493]
  We introduce a novel method for quantifying uncertainty designed to enhance the trustworthiness of LLM-as-a-Judge evaluations. The method quantifies uncertainty by analyzing the relationships between generated assessments and possible ratings. By cross-evaluating these relationships and constructing a confusion matrix based on token probabilities, the method derives labels of high or low uncertainty.
  arXiv  Detail & Related papers  (2024-10-15T13:29:22Z)
• CLUE: Concept-Level Uncertainty Estimation for Large Language Models [49.92690111618016]
  We propose a novel framework for Concept-Level Uncertainty Estimation for Large Language Models (LLMs) We leverage LLMs to convert output sequences into concept-level representations, breaking down sequences into individual concepts and measuring the uncertainty of each concept separately. We conduct experiments to demonstrate that CLUE can provide more interpretable uncertainty estimation results compared with sentence-level uncertainty.
  arXiv  Detail & Related papers  (2024-09-04T18:27:12Z)
• MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty [10.154013836043816]
  We propose a new Multi-Answer Question Answering dataset, MAQA, consisting of world knowledge, mathematical reasoning, and commonsense reasoning tasks. Our findings show that entropy and consistency-based methods estimate the model uncertainty well even under data uncertainty. We believe our observations will pave the way for future work on uncertainty quantification in realistic setting.
  arXiv  Detail & Related papers  (2024-08-13T11:17:31Z)
• Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks [4.167519875804914]
  We present a novel Question Rephrasing technique to evaluate the input uncertainty of large language models (LLMs) This technique is integrated with sampling methods that measure the output uncertainty of LLMs, thereby offering a more comprehensive uncertainty assessment.
  arXiv  Detail & Related papers  (2024-08-07T12:38:23Z)
• A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning [0.8667724053232616]
  We focus on a critical concern for adaptation of Machine Learning in risk-sensitive applications, namely understanding and quantifying uncertainty. Our paper approaches this topic in a structured way, providing a review of the literature in the various facets that uncertainty is enveloped in the ML process. Key contributions in this review are broadening the scope of uncertainty discussion, as well as an updated review of uncertainty quantification methods in Deep Learning.
  arXiv  Detail & Related papers  (2024-06-01T07:17:38Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• DEUP: Direct Epistemic Uncertainty Prediction [56.087230230128185]
  Epistemic uncertainty is part of out-of-sample prediction error due to the lack of knowledge of the learner. We propose a principled approach for directly estimating epistemic uncertainty by learning to predict generalization error and subtracting an estimate of aleatoric uncertainty.
  arXiv  Detail & Related papers  (2021-02-16T23:50:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.