From Words to Numbers: Your Large Language Model Is Secretly A Capable
  Regressor When Given In-Context Examples

Robert Vacareanu; Vlad-Andrei Negru; Vasile Suciu; Mihai Surdeanu

返回文献探索

Paper · arXiv 2404.07544

From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples

Robert Vacareanu, Vlad-Andrei Negru, Vasile Suciu, Mihai Surdeanu

20 upvotesApril 11, 2024arXiv 预印本

AI 摘要

Large language models can perform regression tasks competitively with traditional supervised methods and achieve sub-linear regret with increasing in-context examples.

pre-trained large language modelslinear regressionnon-linear regressionin-context examplessupervised methodsRandom ForestBaggingGradient BoostingFriedman #2 regression datasetAdaBoostSVMKNNsub-linear regretonline learning

Abstract

We analyze how well pre-trained large language models (e.g., Llama2, GPT-4, Claude 3, etc) can do linear and non-linear regression when given in-context examples, without any additional training or gradient updates. Our findings reveal that several large language models (e.g., GPT-4, Claude 3) are able to perform regression tasks with a performance rivaling (or even outperforming) that of traditional supervised methods such as Random Forest, Bagging, or Gradient Boosting. For example, on the challenging Friedman #2 regression dataset, Claude 3 outperforms many supervised methods such as AdaBoost, SVM, Random Forest, KNN, or Gradient Boosting. We then investigate how well the performance of large language models scales with the number of in-context exemplars. We borrow from the notion of regret from online learning and empirically show that LLMs are capable of obtaining a sub-linear regret.