Research map / Large language models / Retrieval and knowledge
Iteratively Questioning and Answering for Interpretable Legal Judgment Prediction
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 |
|---|---|---|---|
| predict via iterative yes/no element questions (QAjudge) instead of direct text classification | LJP · CJO applicable crimes | Macro-F1: 96.9 -> 94.1 | Hurt |
| increase number of questions K from 3 to 9 (ablation) | QAjudge · CJO applicable crimes | Macro-F1: 87.8 -> 94.1 | Helped |
| increase number of elements M from 6 to 29 (ablation) | QAjudge · CJO applicable crimes | Macro-F1: 10.5 -> 95.4 | Helped |
| learned Question Net instead of random question selection (ablation) | QAjudge · CJO | Macro-F1 | Helped |
| LightGBM instead of MLP as Predict Net (ablation) | Predict Net · CJO applicable crimes | Macro-F1: 95.2 -> 95.4 | Helped |
| QA-mode Answer Net instead of multi-label classification (ablation) | Answer Net · CJO elements | Macro-F1: 96.5 -> 96.2 | No clear effect |
Closest papers by meaning
- Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models (AAAI 2024 · similarity 0.84)
- J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning (ICLR 2026 · similarity 0.83)
- JudgeBench: A Benchmark for Evaluating LLM-Based Judges (ICLR 2025 · similarity 0.82)
- LexChain: Modeling Legal Reasoning Chains for Chinese Tort Case Analysis (AAAI 2026 · similarity 0.82)
- LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models (NeurIPS 2024 · similarity 0.82)
- Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge (ICML 2025 · similarity 0.82)
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.