Mastering Classification & Regression with LLMs: Insights from Kaggle Competitions | Philipp Singer

Name: Mastering Classification & Regression with LLMs: Insights from Kaggle Competitions | Philipp Singer
Uploaded: 2023-11-29
Duration: 20 min
Description: H2O's Philipp Singer on applying LLMs to classic classification and regression, comparing zero-shot prompting and more on financial sentiment data.

Generative AI

Overview

In this session, H2O.ai's Philipp Singer explores how large language models can be applied to classical classification and regression problems, not just generative use cases. Using a public financial sentiment dataset from Kaggle, he compares a majority-class baseline, zero-shot LLM prompting, a next-token-probability trick for faster inference, and full fine-tuning with H2O LLM Studio. He also shares results from Kaggle competitions, including a first-place finish in the LLM Science Exam competition, where LLM-based classification outperformed traditional methods.

Key takeaways

Why LLMs, originally built for generative tasks, can also be applied to classical text classification and regression problems
How to get quick zero-shot predictions from an LLM, and the prompt-engineering tradeoffs that make it hard to productionize
A next-token-probability trick that turns a zero-shot LLM into a fast classifier without parsing free-text output
How to fine-tune LLMs for classification and regression in H2O LLM Studio, including adding a custom classification head
Benchmark results from H2O LLM Studio experiments, reaching roughly 94 to 95 percent accuracy on a sentiment task in minutes
How LLM-based classification performed in Kaggle competitions, including a first-place finish in the LLM Science Exam competition

Start owning your AI

One platform. Complete sovereignty. Measurable results.

Request a demo Talk to H2O