AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Language Models are Weak Learners

Hariharan Manikandan, Yiding Jiang, J Zico Kolter

NeurIPS 2023 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use summary-based weak learners with AdaBoost instead of a single Summary predictorGPT-3 Curie tabular classification · 18 UCI and OpenML datasetstest errorImproved
Replace Few-shot examples with a generated SummaryGPT-3 Curie tabular classification · Most tested datasetstest errorImproved
Use five bins with low/medium/high quantifiers for continuous attributes (ablation)Summary · Tabular datasetssummary qualityImproved
Use actual attribute names rather than dummy feature names (ablation)Summary · Tabular classificationfew-shot performanceImproved
Increase support examples in the prompt (ablation)Few-shot · Tabular classificationtest performanceMixed
Increase support examples summarized into the context (ablation)Summary · Tabular classificationtest performanceImproved
Use GPT-generated rather than templatized data descriptions (ablation)Summary · Tabular classificationtest performanceImproved
Use cluster sampling rather than random sampling (ablation)Summary Boosting · Tabular classificationrounds to convergenceImproved
Use cluster rather than random sampling after sufficient boosting rounds (ablation)Summary Boosting · Tabular classificationfinal test errorNo clear effect
Present examples grouped by class rather than shuffled (ablation)Summary · Four datasetstest performanceNo clear effect
Use explicit summary instructions rather than a tl;dr prompt (ablation)Summary · Tabular classificationtest performanceNo clear effect
Use chain-of-thought inference rather than a prefix prompt (ablation)Summary · Tabular classificationtest performanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy