Refining Financial Consumer Complaints through Multi-Scale Model Interaction
This work addresses the need for clearer legal documents in financial disputes, though it appears incremental as it builds on existing LLM techniques for text refinement.
The paper tackled the problem of refining informal financial complaints into persuasive legal arguments by introducing the FinDR dataset and the Multi-Scale Model Interaction (MSMI) method, which significantly outperformed single-pass prompting strategies in experiments.
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.