Pith. sign in

REVIEW 3 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.07544 v3 pith:7YJHZKCY submitted 2024-04-11 cs.CL cs.AI

Robert Vacareanu , Vlad-Andrei Negru , Vasile Suciu , Mihai Surdeanu This is my paper
classification cs.CLcs.AI
keywords languagelargeclaudegradientin-contextmodelsregressionboosting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Towards Compute-Optimal Many-Shot In-Context Learning

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Hybrid demonstration selection that adds 20 similar examples to a large cached random or k-means set matches or beats similarity-only selection at up to 10x lower estimated inference cost in many-shot ICL.

  2. Performance Prediction for Large Systems via Text-to-Text Regression

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A 60M-parameter text-to-text regression model predicts Google Borg cluster efficiency from raw system logs, achieving up to 0.99 rank correlation and 100x lower MSE than tabular baselines.

  3. Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecasting

    cs.LG 2025-06 reject novelty 5.0 of 10

    LLMPred improves LLM-based forecasting by frequency-decomposing inputs and adding an MLP post-processor, but the reported gains largely reflect the trained post-processor and a narrowed multivariate comparison rather ...

Pith tools