# Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction

arXiv: https://arxiv.org/abs/2407.01964 · HTML: https://mlsanity.com/paper/2407.01964/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 9 of 9)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine](https://mlsanity.com/paper/2301.08745/) (2023)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services](https://mlsanity.com/paper/2309.11325/) (2023)

## Built on by (most cited first, 17 of 17)

- [Large Language Models Meet Legal Artificial Intelligence: A Survey](https://mlsanity.com/paper/2509.09969/) (2025)
- [Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning](https://mlsanity.com/paper/2504.02590/) (2025)
- [GLARE: Agentic Reasoning for Legal Judgment Prediction](https://mlsanity.com/paper/2508.16383/) (2025)
- [LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning](https://mlsanity.com/paper/2605.28120/) (2026)
- [LawThinker: A Deep Research Legal Agent in Dynamic Environments](https://mlsanity.com/paper/2602.12056/) (2026)
- [RLJP: Legal Judgment Prediction via First-Order Logic Rule-enhanced with Large Language Models](https://mlsanity.com/paper/2505.21281/) (2025)
- [When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance](https://mlsanity.com/paper/2507.07748/) (2025)
- [INTEGRALBENCH: Benchmarking LLMs with Definite Integral Problems](https://mlsanity.com/paper/2507.21130/) (2025)
- [Universal Legal Article Prediction via Tight Collaboration between Supervised Classification Model and LLM](https://mlsanity.com/paper/2509.22119/) (2025)
- [TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting](https://mlsanity.com/paper/2605.18843/) (2026)
- [The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment](https://mlsanity.com/paper/2605.28464/) (2026)
- [Legal Document Summarization: Enhancing Judicial Efficiency through Automation Detection](https://mlsanity.com/paper/2507.18952/) (2025)
- [LegalChainReasoner: A Legal Chain-guided Framework for Criminal Judicial Opinion Generation](https://mlsanity.com/paper/2509.00783/) (2025)
- [NyayaMind- A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System](https://mlsanity.com/paper/2604.09069/) (2026)
- [Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text](https://mlsanity.com/paper/2605.29076/) (2026)
- [MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short](https://mlsanity.com/paper/2609.09791/) (2026)
- [How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs](https://mlsanity.com/paper/2610.19427/) (2026)

## Abstract (arXiv)

Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and distinguishing between similar charges. To adapt LLMs for effective legal judgment prediction, we introduce the Ask-Discriminate-Predict (ADAPT) reasoning framework inspired by human judicial reasoning. ADAPT involves decomposing case facts, discriminating among potential charges, and predicting the final judgment. We further enhance LLMs through fine-tuning with multi-task synthetic trajectories to improve legal judgment prediction accuracy and efficiency under our ADAPT framework. Extensive experiments conducted on two widely-used datasets demonstrate the superior performance of our framework in legal judgment prediction, particularly when dealing with complex and confusing charges.