$\mathit{\text{Grahak-Nyay:}}$ Consumer Grievance Redressal through Large Language Models

Access to consumer grievance redressal in India is often hindered by procedural complexity, legal jargon, and jurisdictional challenges. To address this, we present $\mathbf{\text{Grahak-Nyay}}$ (Justice-to-Consumers), a chatbot that streamlines the process using open-source Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). Grahak-Nyay simplifies legal complexities through a concise and up-to-date knowledge base. We introduce three novel datasets: $\mathit{\text{GeneralQA}}$ (general consumer law), $\mathit{\text{SectoralQA}}$ (sector-specific knowledge) and $\mathit{\text{SyntheticQA}}$ (for RAG evaluation), along with $\mathit{\text{NyayChat}}$, a dataset of 300 annotated chatbot conversations. We also introduce $\mathit{\text{Judgments}}$ data sourced from Indian Consumer Courts to aid the chatbot in decision making and to enhance user trust. We also propose $\mathbf{\text{HAB}}$ metrics ($\mathbf{\text{Helpfulness,}}\mathbf{\text{Accuracy,}}\mathbf{\text{Brevity}}$) to evaluate chatbot performance. Legal domain experts validated Grahak-Nyay’s effectiveness. Code and datasets will be released.