Research map / Large language models / Retrieval and knowledge
Judgment Prediction via Injecting Legal Knowledge into Neural Networks
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 FOL legal knowledge rules to CoATT | CoATT · Private loan test dataset | Mac.F1: 78.1 -> 79.3 | Helped |
| Add FOL legal knowledge rules to CoATT | CoATT · Private loan test dataset | Mic.F1: 86.4 -> 87.2 | Helped |
| Add legal knowledge rules to CoATT (ablation) | CoATT · Private loan test dataset, 1% training data | Mac-F1: ↑1.88 | Helped |
| Add legal knowledge rules to CoATT (ablation) | CoATT · Private loan test dataset, 1% training data | Mic-F1: 77.93 -> 77.25 | Hurt |
| Add legal knowledge rules to CoATT (ablation) | CoATT · Private loan test dataset, 5% training data | Mac-F1: ↑1.42 | Helped |
| Add legal knowledge rules to CoATT (ablation) | CoATT · Private loan test dataset, 5% training data | Mic-F1: 79.81 -> 79.79 | No clear effect |
| Add legal knowledge rules to CoATT (ablation) | CoATT · Private loan test dataset, 10% training data | Mac-F1: ↑0.86 | Helped |
| Add legal knowledge rule K1 alone (ablation) | CoATT · Private loan test dataset | Mac-F1: 78.09 -> 78.43 | Helped |
| Add legal knowledge rule K2 alone (ablation) | CoATT · Private loan test dataset | Mic-F1: 86.44 -> 86.84 | Helped |
| Add legal knowledge rule K3 alone (ablation) | CoATT · Private loan test dataset | Mac-F1: 78.09 -> 78.33 | Helped |
| Add K1, K2, and K3 together (ablation) | CoATT · Private loan test dataset | Mac-F1: 78.09 -> 79.31 | Helped |
| Add K1, K2, and K3 together (ablation) | CoATT · Private loan test dataset | Mic-F1: 86.44 -> 87.24 | Helped |
Closest papers by meaning
- Neural Reasoning Networks: Efficient Interpretable Neural Networks with Automatic Textual Explanations (AAAI 2025 · similarity 0.82)
- J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain (AAAI 2025 · similarity 0.81)
- LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models (NeurIPS 2024 · similarity 0.80)
- Lawma: The Power of Specialization for Legal Annotation (ICLR 2025 · similarity 0.80)
- Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models (AAAI 2024 · similarity 0.80)
- DELTA: Pre-Train a Discriminative Encoder for Legal Case Retrieval via Structural Word Alignment (AAAI 2025 · similarity 0.80)
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.