Research map / Large language models / Agents, code and math
GENSYNTH: Synthesizing Datalog Programs without Language Bias
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GENSYNTH instead of NTP | Countries benchmark · Countries S1 | F1 score: 1.0 -> 1.0 | No clear effect |
| Use GENSYNTH instead of NTP | Countries benchmark · Countries S1 | time (s): 245.45 -> 14.06 | Helped |
| Use GENSYNTH instead of NTP | Countries benchmark · Countries S2 | F1 score: 0.7586 -> 0.8936 | Helped |
| Use GENSYNTH instead of NTP | Countries benchmark · Countries S2 | time (s): 328.63 -> 3.05 | Helped |
| Use GENSYNTH instead of NTP | Countries benchmark · Countries S3 | F1 score: 0.7547 -> 0.8888 | Helped |
| Use GENSYNTH instead of NTP | Countries benchmark · Countries S3 | time (s): 1660.48 -> 684.82 | Helped |
| Add the reduction phase after accretion | GENSYNTH · 42-task evaluation | program size: 43% decrease | Helped |
| Synthesize without user-provided templates | GENSYNTH · Andersen | time: within 5 minutes on average | Helped |
Closest papers by meaning
- DiscoveryBench: Towards Data-Driven Discovery with Large Language Models (ICLR 2025 · similarity 0.86)
- ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation (AAAI 2026 · similarity 0.85)
- Program Synthesis via Test-Time Transduction (NeurIPS 2025 · similarity 0.85)
- Learning MDL Logic Programs from Noisy Data (AAAI 2024 · similarity 0.85)
- Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus (NeurIPS 2024 · similarity 0.84)
- RuAG: Learned-rule-augmented Generation for Large Language Models (ICLR 2025 · similarity 0.84)
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.