HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications

TL;DR

This paper introduces HR-Agent, a specialized LLM-based dialogue system designed to automate repetitive HR tasks while ensuring confidentiality, addressing a significant gap in applying large language models to sensitive HR processes.

Contribution

The paper presents HR-Agent, a novel confidential, HR-specific task-oriented dialogue system leveraging LLMs to automate repetitive HR processes effectively.

Findings

Preserves confidentiality by not sending conversation data during inference.

Automates tasks like medical claims and access requests efficiently.

Tailored for HR-specific applications with improved privacy and automation.

Abstract

Recent LLM (Large Language Models) advancements benefit many fields such as education and finance, but HR has hundreds of repetitive processes, such as access requests, medical claim filing and time-off submissions, which are unaddressed. We relate these tasks to the LLM agent, which has addressed tasks such as writing assisting and customer support. We present HR-Agent, an efficient, confidential, and HR-specific LLM-based task-oriented dialogue system tailored for automating repetitive HR processes such as medical claims and access requests. Since conversation data is not sent to an LLM during inference, it preserves confidentiality required in HR-related tasks.