Research map / Large language models / AI and society
Goal Driven Discovery of Distributional Differences via Language Descriptions
Ruiqi Zhong, Peter Zhang, Steve Li, Jinwoo Ahn, Dan Klein, Jacob Steinhardt
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 |
|---|---|---|---|
| Condition hypothesis generation on the exploration goal (ablation) | text-davinci-003 · SynD5 | accuracy: 2% -> 12% | Improved |
| Use a validator to select hypotheses (ablation) | text-davinci-003 with goal · SynD5 | accuracy: 4% -> 12% | Improved |
| Use GPT-4 rather than text-davinci-003 as proposer | D5 system with goal and validator · SynD5 | accuracy: 12% -> 27% | Improved |
| Condition hypothesis generation on the exploration goal (ablation) | text-davinci-003 · OpenD5, 100 sampled problems | average relevance rating: 1.20 -> 1.68 | Improved |
| Self-train by selecting hypotheses with the highest estimated validity | Flan-T5-xxl · Mini-problems, groups of four samples | true validity V: 0.07 -> 0.10 | Improved |
| Self-train by selecting hypotheses with the highest estimated validity | Flan-T5-xxl · Mini-problems, groups of four samples | automated validity V': 0.22 to 0.37 | Improved |
| Condition hypothesis generation on the exploration goal (ablation) | text-davinci-003 · OpenD5, 100 sampled problems | average novelty rating: 0.97 -> 1.24 | Improved |
| Condition hypothesis generation on the exploration goal (ablation) | text-davinci-003 · OpenD5, 100 sampled problems | average significance rating: 1.05 -> 1.56 | Improved |
Closest papers by meaning
- What's In My Big Data? (ICLR 2024 · similarity 0.85)
- Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias (NeurIPS 2024 · similarity 0.84)
- End-To-End Causal Effect Estimation from Unstructured Natural Language Data (NeurIPS 2024 · similarity 0.84)
- idSCD: Identifying Training Datasets through Semantic Correlation Descriptors (NeurIPS 2026 · similarity 0.84)
- Revealing Multimodal Causality with Large Language Models (NeurIPS 2025 · similarity 0.83)
- CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research (NeurIPS 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.
