Research map / Vision-language and multimodal / Visual question answering
Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning
Jiani Huang, Ziyang Li, Binghong Chen, Karan Samel, Mayur Naik, Le Song, Xujie Si
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 |
|---|---|---|---|
| Scallop top-k differentiable reasoning versus Neural Module Networks | VQAR · VQAR 5000 Call | Recall@5: 71.80% -> 84.22% | Improved |
| Scallop versus LXMERT | VQAR · VQAR 5000 Call | Recall@5: 62.56% -> 84.22% | Improved |
| remove differentiability, use REINFORCE with discrete scene graph sampling (Datalog-RL) (ablation) | Scallop · VQAR generalization to harder questions | Recall@5 | Hurt |
| increase k from 1 to 5 in training (ablation) | Scallop · sum3 | convergence stability | Improved |
| increase k from 1 to 15 at inference (ablation) | Scallop · sum3 | inference time (s): 0.05 -> 6.15 | Hurt |
| use smaller ktest than ktrain=10 at test time (ablation) | Scallop · sum3 | accuracy difference vs ktest=10 | No clear effect |
| Scallop top-k versus exact DeepProbLog | synthetic MNIST tasks · 6 synthetic tasks | accuracy | No clear effect |
Closest papers by meaning
- Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation (ICLR 2025 · similarity 0.85)
- SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks (AAAI 2025 · similarity 0.85)
- LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning (AAAI 2026 · similarity 0.85)
- CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs (NeurIPS 2026 · similarity 0.85)
- CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning (ICLR 2025 · similarity 0.85)
- Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought (NeurIPS 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.
