# Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning

arXiv: https://arxiv.org/abs/2406.03600 · HTML: https://mlsanity.com/paper/2406.03600/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 38 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents](https://mlsanity.com/paper/2105.03887/) (2021)
- [Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training](https://mlsanity.com/paper/2006.11280/) (2020)
- [Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective](https://mlsanity.com/paper/2212.02801/) (2022)
- [Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions](https://mlsanity.com/paper/1802.08504/) (2018)
- [Community-Based Hierarchical Positive-Unlabeled (PU) Model Fusion for Chronic Disease Prediction](https://mlsanity.com/paper/2309.03386/) (2023)

## Built on by (most cited first, 12 of 12)

- [MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations](https://mlsanity.com/paper/2506.20100/) (2025)
- [FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets](https://mlsanity.com/paper/2505.19819/) (2025)
- [ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning](https://mlsanity.com/paper/2412.00631/) (2024)
- [Intelligent Legal Assistant: An Interactive Clarification System for Legal Question Answering](https://mlsanity.com/paper/2502.07904/) (2025)
- [Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs](https://mlsanity.com/paper/2511.15163/) (2025)
- [LeCoDe: A Benchmark Dataset for Interactive Legal Consultation Dialogue Evaluation](https://mlsanity.com/paper/2505.19667/) (2025)
- [Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains](https://mlsanity.com/paper/2508.17202/) (2025)
- ["Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations](https://mlsanity.com/paper/2604.15588/) (2026)
- [Auto-Drafting Police Reports from Noisy ASR Outputs: A Trust-Centered LLM Approach](https://mlsanity.com/paper/2502.07677/) (2025)
- [Aplicacc~ao de Large Language Models na An'alise e S'intese de Documentos Jur'idicos: Uma Revis~ao de Literatura](https://mlsanity.com/paper/2504.00725/) (2025)
- [BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation](https://mlsanity.com/paper/2609.10815/) (2026)
- [CamPilot: A Multi-Agent Cinematic Assistant for Camera-Controlled Movie Generation](https://mlsanity.com/paper/2609.10943/) (2026)

## Abstract (arXiv)

The integration of generative Large Language Models (LLMs) into various applications, including the legal domain, has been accelerated by their expansive and versatile nature. However, when facing a legal case, users without a legal background often struggle to formulate professional queries and may inadvertently overlook critical legal factors when presenting their case narrative to LLMs. To address this issue, we propose the Diagnostic Legal Large Language Model (D3LM), which utilizes adaptive lawyer-like diagnostic questions to collect additional case information and then provides high-quality feedback. D3LM incorporates an innovative graph-based Positive-Unlabeled Reinforcement Learning (PURL) algorithm, enabling the generation of critical questions and enhancing user-LLM interactions. Moreover, an integrated LLM-based stopping criterion facilitates precise Court Views Generation (CVG). Our research also introduces a new English-language CVG dataset based on the US case law database, enriching the realm of LLM research and deployment with a vital dimension. D3LM surpasses classical LLMs by delivering outstanding performance and a remarkable user experience in the legal domain.