Research map / Large language models / Retrieval and knowledge
Enabling Knowledge Refinement upon New Concepts in Abductive Learning
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 |
|---|---|---|---|
| Add learned new-concept rules and refine the knowledge base during abductive learning | ABL · Less-Than with New Digits | reasoning accuracy: 0.904±0.009 -> 0.986±0.005 | Helped |
| Add learned new-concept rules and refine the knowledge base during abductive learning | ABL · Less-Than with New Digits | perception accuracy: 0.959±0.015 -> 0.975±0.005 | Helped |
| Add learned new-concept rules and refine the knowledge base during abductive learning | ABL · Chess with New Pieces | reasoning accuracy: 0.937±0.009 -> 0.984±0.005 | Helped |
| Add learned new-concept rules and refine the knowledge base during abductive learning | ABL · Chess with New Pieces | perception accuracy: 0.930±0.015 -> 0.990±0.006 | Helped |
| Add learned new-concept rules and resolve conflicts with existing knowledge | ABL · Multiples of Three | reasoning accuracy: 0.639±0.011 -> 0.963±0.004 | Helped |
| Add learned new-concept rules and resolve conflicts with existing knowledge | ABL · Multiples of Three | perception accuracy: 0.938±0.005 -> 0.960±0.008 | Helped |
| Add new-concept rules directly without resolving conflicts in the knowledge base | CNNnew · Multiples of Three | reasoning accuracy: 0.601±0.019 -> 0.323±0.012 | Hurt |
Closest papers by meaning
- Curriculum Abductive Learning (NeurIPS 2025 · similarity 0.90)
- Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts (ICML 2024 · similarity 0.88)
- Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection (AAAI 2025 · similarity 0.88)
- Ambiguity-Aware Abductive Learning (ICML 2024 · similarity 0.85)
- Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees (AAAI 2024 · similarity 0.84)
- Safe Abductive Learning in the Presence of Inaccurate Rules (AAAI 2024 · 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.