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

TL;DR

Grahak-Nyay is a chatbot leveraging large language models and retrieval techniques to simplify consumer grievance redressal in India, supported by new datasets and evaluation metrics validated by legal experts.

Contribution

The paper introduces Grahak-Nyay, a novel LLM-based chatbot for consumer grievances, along with new datasets, evaluation metrics, and validation in the Indian legal context.

Findings

Grahak-Nyay effectively simplifies legal procedures for consumers.

The new datasets improve chatbot training and evaluation.

Legal experts validate the chatbot's performance and trustworthiness.

Abstract

Access to consumer grievance redressal in India is often hindered by procedural complexity, legal jargon, and jurisdictional challenges. To address this, we present $\textbf{Grahak-Nyay}$ (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: $\textit{GeneralQA}$ (general consumer law), $\textit{SectoralQA}$ (sector-specific knowledge) and $\textit{SyntheticQA}$ (for RAG evaluation), along with $\textit{NyayChat}$, a dataset of 300 annotated chatbot conversations. We also introduce $\textit{Judgments}$ data sourced from Indian Consumer Courts to aid the chatbot in decision making and to enhance user trust. We also propose $\textbf{HAB}$ metrics ($\textbf{Helpfulness, Accuracy, Brevity}$) to evaluate chatbot performance. Legal domain experts validated Grahak-Nyay's effectiveness. Code and datasets will be released.