paper-with-me

Papers

On Subjective Uncertainty Quantification and Calibration in Natural Language Generation

2024-06-07 · Ziyu Wang, Chris Holmes

Applications of large language models often involve the generation of free-form responses, in which case uncertainty quantification becomes challenging. This is due to the need to identify task-specific uncertainties (e.g., about the semantics) which appears difficult to define in general cases. This work addresses these challenges from a perspective of Bayesian decision theory, starting from the assumption that our utility is characterized by a similarity measure that compares a generated response with a hypothetical true response. We discuss how this assumption enables principled quantification of the model's subjective uncertainty and its calibration. We further derive a measure for epistemic uncertainty, based on a missing data perspective and its characterization as an excess risk. The proposed methods can be applied to black-box language models. We illustrate the methods on question answering and machine translation tasks. Our experiments provide a principled evaluation of task-specific calibration, and demonstrate that epistemic uncertainty offers a promising deferral strategy for efficient data acquisition in in-context learning.

📄 PDF Abstract BibTeX arXiv:2406.05213

Code (1)

meta-inf/suq-nlg 공식 구현

Tasks

In-Context LearningMachine TranslationQuestion AnsweringText GenerationUncertainty Quantification

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

A Novel Framework for Uncertainty Quantification via Proper Scores for Classification and Beyond

2025-08-25 · Sebastian G. Gruber arxiv

In this PhD thesis, we propose a novel framework for uncertainty quantification in machine learning, which is based on proper scores. Uncertainty quantification is an important cornerstone for trustworthy and reliable ma…

Multi-group Uncertainty Quantification for Long-form Text Generation

2024-07-25 · Terrance Liu, Zhiwei Steven Wu

While large language models are rapidly moving towards consumer-facing applications, they are often still prone to factual errors and hallucinations. In order to reduce the potential harms that may come from these errors…

Conformal PredictionFormLanguage ModellingLarge Language Model+3

A Study on the Calibration of In-context Learning

2023-12-07 · HANLIN ZHANG, Yi-Fan Zhang, Yaodong Yu, Dhruv Madeka 외

Accurate uncertainty quantification is crucial for the safe deployment of machine learning models, and prior research has demonstrated improvements in the calibration of modern language models (LMs). We study in-context …

In-Context LearningNatural Language UnderstandingUncertainty Quantification

Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification

2025-07-09 · Maya Kruse, Majid Afshar, Saksham Khatwani, Anoop Mayampurath 외 arxiv

Large language models (LLMs) often behave inconsistently across inputs, indicating uncertainty and motivating the need for its quantification in high-stakes settings. Prior work on calibration and uncertainty quantificat…

Subjective Risk Decomposition: A New View for Uncertainty Quantification

2026-07-16 · Raghad Alamri, Michele Caprio, Gavin Brown arxiv

We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead consequences, of higher-level modelling decisions. We show how episte…