Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs

• URL: http://arxiv.org/abs/2406.11278v2
• Date: Fri, 18 Oct 2024 02:28:29 GMT
• Title: Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
• Authors: Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates, Chenyang Tao, Anil Ramakrishna, Dimitrios Dimitriadis, Jieyu Zhao, Salman Avestimehr,
• Abstract summary: Learnable Response Scoring (LARS) is a novel scoring function that leverages supervised data to capture complex dependencies between tokens and probabilities. Our experiments demonstrate that LARS significantly outperforms existing scoring functions, achieving improvements of up to 16% AUROC score.
• Score: 32.672370840879616
• License:
• Abstract: Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize token probabilities to assess uncertainty, aggregating multiple token probabilities into a single UE score using a scoring function. Existing scoring functions for probability-based UE, such as length-normalized scoring and semantic contribution-based weighting, are designed to solve certain aspects of the problem but exhibit limitations, including the inability to handle biased probabilities and complex semantic dependencies between tokens. To address these issues, in this work, we propose Learnable Response Scoring (LARS) function, a novel scoring function that leverages supervised data to capture complex dependencies between tokens and probabilities, thereby producing more reliable and calibrated response scores in computing the uncertainty of LLM generations. Our comprehensive experiments across question-answering and arithmetical reasoning tasks with various datasets demonstrate that LARS significantly outperforms existing scoring functions, achieving improvements of up to 16\% AUROC score.

Related papers

• Statistical Test for Auto Feature Engineering by Selective Inference [12.703556860454565]
  Auto Feature Engineering (AFE) plays a crucial role in developing practical machine learning pipelines. We propose a new statistical test for generated features by AFE algorithms based on a framework called selective inference. The proposed test can quantify the statistical significance of the generated features in the form of $p$-values, enabling theoretically guaranteed control of the risk of false findings.
  arXiv  Detail & Related papers  (2024-10-13T12:26:51Z)
• Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation [37.63939774027709]
  We propose enhancing the predicted sequence probability by assigning different weights to various tokens. We refer to this new score as the Contextualized Sequence Likelihood (CSL)
  arXiv  Detail & Related papers  (2024-06-03T21:55:07Z)
• BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models [52.46248487458641]
  Predictive models often need to work with incomplete information in real-world tasks. Current large language models (LLM) are insufficient for such accurate estimations. We propose BIRD, a novel probabilistic inference framework.
  arXiv  Detail & Related papers  (2024-04-18T20:17:23Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• 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)
• Toward Robust Uncertainty Estimation with Random Activation Functions [3.0586855806896045]
  We propose a novel approach for uncertainty quantification via ensembles, called Random Activation Functions (RAFs) Ensemble. RAFs Ensemble outperforms state-of-the-art ensemble uncertainty quantification methods on both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-02-28T13:17:56Z)
• Bayesian sequential design of computer experiments for quantile set inversion [0.0]
  We consider an unknown multivariate function representing a system-such as a complex numerical simulator. Our objective is to estimate the set of deterministic inputs leading to outputs whose probability is less than a given threshold.
  arXiv  Detail & Related papers  (2022-11-02T10:14:05Z)
• Diversity Enhanced Active Learning with Strictly Proper Scoring Rules [4.81450893955064]
  We study acquisition functions for active learning (AL) for text classification. We convert the Expected Loss Reduction (ELR) method to estimate the increase in (strictly proper) scores like log probability or negative mean square error. We show that the use of mean square error and log probability with BEMPS yields robust acquisition functions.
  arXiv  Detail & Related papers  (2021-10-27T05:02:11Z)
• Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap [140.98628848491146]
  We introduce deconfounding scores, which induce better overlap without biasing the target of estimation. We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data. In particular, we show that this technique could be an attractive alternative to standard regularizations.
  arXiv  Detail & Related papers  (2021-04-12T18:50:11Z)
• Estimating Structural Target Functions using Machine Learning and Influence Functions [103.47897241856603]
  We propose a new framework for statistical machine learning of target functions arising as identifiable functionals from statistical models. This framework is problem- and model-agnostic and can be used to estimate a broad variety of target parameters of interest in applied statistics. We put particular focus on so-called coarsening at random/doubly robust problems with partially unobserved information.
  arXiv  Detail & Related papers  (2020-08-14T16:48:29Z)
• Causal Feature Selection for Algorithmic Fairness [61.767399505764736]
  We consider fairness in the integration component of data management. We propose an approach to identify a sub-collection of features that ensure the fairness of the dataset.
  arXiv  Detail & Related papers  (2020-06-10T20:20:10Z)

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.