AI and Deep Learning

How do we mitigate bias and toxicity when fine-tuning Large Language Models for customer service?

PA Asked by Patricia White · 20-05-2023
0 upvotes 7,238 views 0 comments
The question

We are about to deploy a fine-tuned LLM for our customer support portal, but we are terrified of the model generating biased or inappropriate responses. What are the best industry practices for "Alignment" and safety filtering? Are there specific datasets or Reinforcement Learning from Human Feedback (RLHF) techniques that a medium-sized company can realistically implement without a massive budget? 

3 answers

0
M
Answered on 22-05-2023

Alignment is a major challenge. I recommend starting with "Constitutional AI" principles—giving the model a set of rules it must follow during the fine-tuning phase. For a medium budget, you don't necessarily need full RLHF. You can use "Supervised Fine-Tuning" (SFT) on a high-quality, curated dataset of "gold standard" customer interactions. Additionally, implement a "guardrail" layer using a secondary, smaller model that checks the output for toxicity before it ever reaches the customer. Tools like NeMo Guardrails can help you set up these boundaries effectively without needing a team of PhDs to manage it. 

0
JA
Answered on 24-05-2023

Are you planning to use a closed-source model like OpenAI's API which has built-in filters, or are you running an open-source model like Llama-3 on your own private servers?

PA 26-05-2023

James, we are using Llama-3 for data privacy reasons, so we are responsible for all the filtering ourselves. That's why I'm so focused on finding robust open-source libraries. We need to make sure the model doesn't accidentally hallucinate fake return policies or use language that could be seen as discriminatory. Michelle’s suggestion about NeMo Guardrails seems like exactly the kind of middleware we were looking for to sit between the model and the user.

0
TH
Answered on 28-05-2023

You should definitely look into "Red Teaming" your model. Have your team intentionally try to break it or trick it into saying something bad before you go live.

PA 29-05-2023

Red teaming is essential, Thomas. It’s the only way to find those weird edge cases where the model might fail in a way you never expected during standard testing.

Share your thoughts

Your email address will not be published. Required fields are marked (*)

Professional Counselling Session

Still have questions?
Schedule a free counselling session

Our experts are ready to help you with any questions about courses, admissions, or career paths. Get personalized guidance from industry professionals.

Request a Call Back

Search Online

We Accept

We Accept

Follow Us

"PMI®", "PMBOK®", "PMP®", "CAPM®" and "PMI-ACP®" are registered marks of the Project Management Institute, Inc. | "CSM", "CST" are Registered Trade Marks of The Scrum Alliance, USA. | COBIT® is a trademark of ISACA® registered in the United States and other countries.

Book Free Session