Research map / Large language models / Retrieval and knowledge
Identifying Useful Inference Paths in Large Commonsense Knowledge Bases by Retrograde Analysis
Abhishek Sharma, Keith Goolsbey
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 |
|---|---|---|---|
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 1 | % queries answered: 97 -> 98 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 2 | % queries answered: 60 -> 91 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 3 | % queries answered: 23 -> 80 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 4a | % queries answered: 8 -> 97 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 4b | % queries answered: 20 -> 97 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 1 | time (hours): 0.79 -> 0.38 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 2 | time (hours): 17.84 -> 2.52 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 3 | time (hours): 63.13 -> 11.27 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 4a | time (hours): 109.22 -> 5.08 | Improved |
| Add retrograde-analysis proof-path heuristic module (wc=1 vs wc=0) | Cyc inference engine · Cyc test set 4b | time (hours): 66.91 -> 3.51 | Improved |
Closest papers by meaning
- Accelerating Large Language Model Reasoning via Speculative Search (ICML 2025 · similarity 0.87)
- A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings (NeurIPS 2025 · similarity 0.87)
- Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation (ICML 2025 · similarity 0.87)
- Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Trace (NeurIPS 2026 · similarity 0.87)
- MindMap: Constructing Evidence Chains for Multi-Step Reasoning in Large Language Models (AAAI 2024 · similarity 0.86)
- Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts (ICLR 2026 · similarity 0.86)
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.
