Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.19464 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914495102713856 |
|---|---|
| author | Wang, Fanyu Kang, Xiaoxi Burgess, Paul Srivastava, Aashish Arora, Chetan Trakic, Adnan Soon, Lay-Ki Hossain, Md Khalid Qu, Lizhen |
| author_facet | Wang, Fanyu Kang, Xiaoxi Burgess, Paul Srivastava, Aashish Arora, Chetan Trakic, Adnan Soon, Lay-Ki Hossain, Md Khalid Qu, Lizhen |
| contents | More than half of the global population struggles to meet their civil justice needs due to limited legal resources. While Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, significant challenges remain even at the foundational step of legal issue identification. To investigate LLMs' capabilities in this task, we constructed a dataset from 769 real-world Malaysian Contract Act court cases, using GPT-4o to extract facts and generate candidate legal issues, annotated by senior legal experts, which reveals a critical limitation: while LLMs generate diverse issue candidates, their precision remains inadequate (GPT-4o achieves only 62%). To address this gap, we propose LePREC (Legal Professional-inspired Reasoning Elicitation and Classification), a neuro-symbolic framework combining neural generation with structured statistical reasoning. LePREC consists of: (1) a neuro component leverages LLMs to transform legal descriptions into question-answer pairs representing diverse analytical factors, and (2) a symbolic component applies sparse linear models over these discrete features, learning explicit algebraic weights that identify the most informative reasoning factors. Unlike end-to-end neural approaches, LePREC achieves interpretability through transparent feature weighting while maintaining data efficiency through correlation-based statistical classification. Experiments show a 30-40% improvement over advanced LLM baselines, including GPT-4o and Claude, confirming that correlation-based factor-issue analysis offers a more data-efficient solution for relevance decisions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19464 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues Wang, Fanyu Kang, Xiaoxi Burgess, Paul Srivastava, Aashish Arora, Chetan Trakic, Adnan Soon, Lay-Ki Hossain, Md Khalid Qu, Lizhen Computation and Language Artificial Intelligence More than half of the global population struggles to meet their civil justice needs due to limited legal resources. While Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, significant challenges remain even at the foundational step of legal issue identification. To investigate LLMs' capabilities in this task, we constructed a dataset from 769 real-world Malaysian Contract Act court cases, using GPT-4o to extract facts and generate candidate legal issues, annotated by senior legal experts, which reveals a critical limitation: while LLMs generate diverse issue candidates, their precision remains inadequate (GPT-4o achieves only 62%). To address this gap, we propose LePREC (Legal Professional-inspired Reasoning Elicitation and Classification), a neuro-symbolic framework combining neural generation with structured statistical reasoning. LePREC consists of: (1) a neuro component leverages LLMs to transform legal descriptions into question-answer pairs representing diverse analytical factors, and (2) a symbolic component applies sparse linear models over these discrete features, learning explicit algebraic weights that identify the most informative reasoning factors. Unlike end-to-end neural approaches, LePREC achieves interpretability through transparent feature weighting while maintaining data efficiency through correlation-based statistical classification. Experiments show a 30-40% improvement over advanced LLM baselines, including GPT-4o and Claude, confirming that correlation-based factor-issue analysis offers a more data-efficient solution for relevance decisions. |
| title | LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.19464 |