Research map / Large language models / Language, safety and interpretability
RAFT: A Real-World Few-Shot Text Classification Benchmark
Neel Alex, Eli Lifland, Lewis Tunstall, Abhishek Thakur, Pegah Maham, C. Jess Riedel, Emmie Hine, Carolyn Ashurst, Paul Sedille, Alexis Carlier, Michael Noetel, Andreas Stuhlmüller
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use task-specific instructions instead of a generic classification prompt | GPT-3 in-context RAFT baseline · RAFT average | macro F1: .04 averaged F1 | Improved |
| Select semantically similar training examples instead of random examples | GPT-3 in-context RAFT baseline · RAFT average | macro F1: 0.03 on averaged F1 | Improved |
| Use crowdsourced humans rather than GPT-3 (175B) | RAFT tasks · RAFT average | macro F1: 0.11 | Improved |
| Use GPT-3 few-shot rather than GPT-3 zero-shot | RAFT · RAFT average | macro F1: .292 -> .627 | Improved |
Closest papers by meaning
- Task Contamination: Language Models May Not Be Few-Shot Anymore (AAAI 2024 · similarity 0.84)
- The Surprising Effectiveness of Test-Time Training for Few-Shot Learning (ICML 2025 · similarity 0.83)
- MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans? (ICLR 2025 · similarity 0.83)
- Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing (AAAI 2024 · similarity 0.83)
- Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning (CVPR 2025 · similarity 0.83)
- WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild (ICLR 2025 · similarity 0.83)
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.
