Refining Financial Consumer Complaints through Multi-Scale Model Interaction
Preprint
Abstract
Legal writing demands clarity, formality, and domain-specific precision-qualities often lacking in documents authored by individuals without legal training. To bridge this gap, this paper explores the task of legal text refinement that transforms informal, conversational inputs into persuasive legal arguments. We introduce FinDR, a Chinese dataset of financial dispute records, annotated with official judgments on claim reasonableness. Our proposed method, Multi-Scale Model Interaction (MSMI), leverages a lightweight classifier to evaluate outputs and guide iterative refinement by Large Language Models (LLMs). Experimental results demonstrate that MSMI significantly outperforms single-pass prompting strategies. Additionally, we validate the generalizability of MSMI on several short-text benchmarks, showing improved adversarial robustness. Our findings reveal the potential of multi-model collaboration for enhancing legal document generation and broader text refinement tasks.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement2024
- Self-Refine: Iterative Refinement with Self-Feedback2023
- Reflexion: language agents with verbal reinforcement learning2023
- DISCO: Distilling Counterfactuals with Large Language Models2023
- CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation2022
- Retrieval-guided Counterfactual Generation for QA2022
- Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for TextProceedings of the AAAI Conference on Artificial Intelligence, 2021
- A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference2018