ArgAssist: LLM-based Argument Synthesis for Insurance Disputes

Access to timely and affordable dispute resolution is a major challenge for industries such as insurance, finance, and consumer goods, where legal disputes between suppliers and consumers are frequent and often complex. We present "ArgAssist", which is an LLM-powered module at the core of an alternative dispute resolution (ADR) platform that we are building. ArgAssist assists parties involved in a dispute (such as insurer and insured in an insurance dispute) in formulating structured legal arguments based on case facts and points of contention. ArgAssist first generates 'base' arguments using an LLM and these arguments are further strengthened by grounding them in relevant prior cases and statutes ensuring legal soundness and contextual relevance. We introduce a novel evaluation metric for assessing the quality of generated arguments and demonstrate ArgAssist’s effectiveness on two real world datasets in the insurance domain.