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

Research Area: Science of LMs

Keywords: regression, emergent capabilities

TL;DR: Large Language Models can do linear and non-linear regression when given in-context examples, sometimes better than specialized methods such as Gradient Boosting or Random Forest

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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1043