# LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction

arXiv: https://arxiv.org/abs/2603.11446 · HTML: https://mlsanity.com/paper/2603.11446/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset](https://mlsanity.com/paper/2104.08671/) (2021)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [Portuguese Named Entity Recognition using BERT-CRF](https://mlsanity.com/paper/1909.10649/) (2019)
- [Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark](https://mlsanity.com/paper/2110.00806/) (2021)
- [LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development](https://mlsanity.com/paper/2305.07507/) (2023)
- [Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law](https://mlsanity.com/paper/2209.06049/) (2022)
- [LEVEN: A Large-Scale Chinese Legal Event Detection Dataset](https://mlsanity.com/paper/2203.08556/) (2022)
- [Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer](https://mlsanity.com/paper/2211.00974/) (2022)
- [Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis](https://mlsanity.com/paper/2104.09420/) (2021)
- [LawInstruct: A Resource for Studying Language Model Adaptation to the Legal Domain](https://mlsanity.com/paper/2404.02127/) (2024)
- [Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction](https://mlsanity.com/paper/2504.05358/) (2025)
- [Legal Transformer Models May Not Always Help](https://mlsanity.com/paper/2109.06862/) (2021)
- [The Unreasonable Effectiveness of the Baseline: Discussing SVMs in Legal Text Classification](https://mlsanity.com/paper/2109.07234/) (2021)
- [LegaLMFiT: Efficient Short Legal Text Classification with LSTM Language Model Pre-Training](https://mlsanity.com/paper/2109.00993/) (2021)
- [LLMEmbed: Rethinking Lightweight LLM's Genuine Function in Text Classification](https://mlsanity.com/paper/2406.03725/) (2024)
- [Improving the Accuracy and Efficiency of Legal Document Tagging with Large Language Models and Instruction Prompts](https://mlsanity.com/paper/2504.09309/) (2025)

## Abstract (arXiv)

Mainstream methods for Legal Judgment Prediction (LJP) based on Pre-trained Language Models (PLMs) heavily rely on the statistical correlation between case facts and judgment results. This paradigm lacks explicit modeling of legal constituent elements and underlying causal logic, making models prone to learning spurious correlations and suffering from poor robustness. While introducing causal inference can mitigate this issue, existing causal LJP methods face two critical bottlenecks in real-world legal texts: inaccurate legal factor extraction with severe noise, and significant uncertainty in causal structure discovery due to Markov equivalence under sparse features. To address these challenges, we propose an enhanced causal inference framework that integrates Large Language Model (LLM) priors with statistical causal discovery. First, we design a coarse-to-fine hybrid extraction mechanism combining statistical sampling and LLM semantic reasoning to accurately identify and purify standard legal constituent elements. Second, to resolve structural uncertainty, we introduce an LLM-assisted causal structure disambiguation mechanism. By utilizing the LLM as a constrained prior knowledge base, we conduct probabilistic evaluation and pruning on ambiguous causal directions to generate legally compliant candidate causal graphs. Finally, a causal-aware judgment prediction model is constructed by explicitly constraining text attention intensity via the generated causal graphs. Extensive experiments on multiple benchmark datasets, including LEVEN , QA, and CAIL, demonstrate that our proposed method significantly outperforms state-of-the-art baselines in both predictive accuracy and robustness, particularly in distinguishing confusing charges.