Research map / Learning theory and algorithms / Combinatorial and search optimization
FastLAS: Scalable Inductive Logic Programming Incorporating Domain-Specific Optimisation Criteria
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 FastLAS instead of ILASP3 (same length scoring) | ILP system · Sentence chunking, 500 examples | running time: 1051.4s -> 4.5s | Helped |
| use FastLAS instead of ILASP3 | ILP system · Sentence chunking, 500 examples | F1: 0.777 -> 0.768 | No clear effect |
| use FastLAS instead of INSPIRE | ILP system · Sentence chunking, 100 examples | F1: 0.733 -> 0.751 | Helped |
| use FastLAS with larger hypothesis space instead of ILASP3 | ILP system · CAVIAR | F1: 0.837 -> 0.907 | Helped |
| use FastLAS instead of ILASP3 | ILP system · CAVIAR | running time: 523.3s -> 263.8s | Helped |
| use FastLAS instead of OLED | ILP system · CAVIAR | running time: 107s -> 263.8s | Hurt |
| switch scoring from S_len to S_uni (favor generalisation) (ablation) | FastLAS accept rules · Amazon | recall: 0.782 -> 0.820 | Helped |
| switch scoring from S_len to S_uni (ablation) | FastLAS accept rules · Project Management | precision: 0.951 -> 0.917 | Hurt |
| switch scoring from S_len to S_uni (ablation) | FastLAS accept rules · Project Management | F1: 0.928 -> 0.952 | Helped |
| switch from S_len to S_UF1 penalizing over-generality (ablation) | FastLAS · Amazon resource 25993 | UF1: 0.02 -> 0.07 | Helped |
Closest papers by meaning
- Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus (NeurIPS 2024 · similarity 0.84)
- Inductive Learning of Logical Theories with LLMs: A Expressivity-graded Analysis (AAAI 2025 · similarity 0.83)
- Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation (ICLR 2025 · similarity 0.83)
- Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment (ICML 2025 · similarity 0.83)
- Logic.py: Bridging the Gap between LLMs and Constraint Solvers (NeurIPS 2025 · similarity 0.83)
- Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning (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.