A Recipe For Building a Compliant Real Estate Chatbot

Navid Madani, Anusha Bagalkotkar, Supriya Anand, Gabriel Arnson, Rohini Srihari +1 more
10/7/2024
cs.CLcs.AI

No official code found. Best implementation: zillow/compliant-real-estate-chatbot (19 stars, last commit 2025-03-21).

Abstract

In recent years, there has been significant effort to align large language models with human preferences. This work focuses on developing a chatbot specialized in the real estate domain, with an emphasis on incorporating compliant behavior to ensure it can be used without perpetuating discriminatory practices like steering and redlining, which have historically plagued the real estate industry in the United States. Building on prior work, we present a method for generating a synthetic general instruction-following dataset, along with safety data. Through extensive evaluations and benchmarks, we fine-tuned a llama-3-8B-instruct model and demonstrated that we can enhance it's performance significantly to match huge closed-source models like GPT-4o while making it safer and more compliant. We open-source the model, data and code to support further development and research in the community.

View on arXivView PDF

Code Implementations(1)

zillow/compliant-real-estate-chatbotCommunity100%

Code and experiments for the paper "A recipe for building a compliant real estate chatbot"

193Shell, PythonOct 1, 20241 years agoNOASSERTION

Similar Papers

Towards Safer Chatbots: Automated Policy Compliance Evaluation of Custom GPTs

82% match2025

Prompt Engineering a Schizophrenia Chatbot: Utilizing a Multi-Agent Approach for Enhanced Compliance with Prompt Instructions

80% match2024

ChatbotManip: A Dataset to Facilitate Evaluation and Oversight of Manipulative Chatbot Behaviour

79% match2025

REAL: Benchmarking Abilities of Large Language Models for Housing Transactions and Services

79% match2025

From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training

78% match2025

Towards Healthy AI: Large Language Models Need Therapists Too

78% match2023

Cite this paper

@article{madani2024recipe,
  title  = {A Recipe For Building a Compliant Real Estate Chatbot},
  author = {Navid Madani and Anusha Bagalkotkar and Supriya Anand and Gabriel Arnson and Rohini Srihari and Kenneth Joseph},
  year   = {2024},
  eprint = {2410.10860},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.10860v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.10860.svg)](https://codeofpaper.com/paper/2410.10860)

Discussion