A Recipe For Building a Compliant Real Estate Chatbot
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913545517531136 |
|---|---|
| author | Madani, Navid Bagalkotkar, Anusha Anand, Supriya Arnson, Gabriel Srihari, Rohini Joseph, Kenneth |
| author_facet | Madani, Navid Bagalkotkar, Anusha Anand, Supriya Arnson, Gabriel Srihari, Rohini Joseph, Kenneth |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10860 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Recipe For Building a Compliant Real Estate Chatbot Madani, Navid Bagalkotkar, Anusha Anand, Supriya Arnson, Gabriel Srihari, Rohini Joseph, Kenneth Computation and Language Artificial Intelligence 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. |
| title | A Recipe For Building a Compliant Real Estate Chatbot |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.10860 |