皇冠体育app

Background & Description

More organisations are starting to use chatbots for many purposes, including interacting with individuals in ways that could result in harm from differential treatment in terms of the user鈥檚 demographic status. FairNow鈥檚 chatbot bias assessment provides a way for chatbot deployers to test for bias. This bias evaluation methodology relies on the generation of prompts (messages sent to the chatbot) that are realistic and representative of how individuals interact with the chatbot.

In order to test for bias in a chatbot, FairNow鈥檚 platform populates a suite of relevant prompts with information that associates the prompt with an individual鈥檚 race or gender. 皇冠体育app evaluation analyses differences in responses between demographic groups to understand if the chatbot treats members of a different group more or less favorably. 皇冠体育app evaluation varies by prompt type in terms of the specific content being assessed. Where customers have logs of previous chatbot interactions and are able to share them, FairNow leverages those logs as context to ensure the bias evaluation reflects user queries and engagement in terms of content, style, and tone.

How this technique applies to the AI White Paper Regulatory Principles

Safety, Security & Robustness

FairNow鈥檚 bias evaluation methodology allows chatbot deployers to test their application for bias. 皇冠体育app evaluation can be applied before the chatbot is released, ensuring that the risk of bias is assessed before being placed in front of individuals. It can also be applied when changes are planned to ensure updated versions of the chatbot are not biased.

FairNow鈥檚 bias evaluation methodology is not designed to test for safety or security.

FairNow鈥檚 bias evaluation methodology can be used to evaluate a chatbot for robustness. By evaluating the quality of responses when the subject is inferred to belong to different demographic groups, FairNow鈥檚 evaluation can ensure the chatbot is robust in this way. 皇冠体育app input prompts include a level of variety in style and word choice to further test that the chatbot responds in a consistent manner to the same message.

Fairness

This methodology includes an evaluation of chatbot responses to subjects of different races and genders. FairNow鈥檚 methodology applies various techniques to measure the favorability of responses in order to measure differences in responses by demographic group.

Accountability & Governance

Bias evaluation results enable the organisation to take accountability for ensuring their chatbots are safe. 皇冠体育app results can also be tied to the laws and standards the organisation adheres to in order to demonstrate compliance.

Why we took this approach

皇冠体育app evaluation of bias in chatbots and large language models is a new and evolving space. Companies looking to deploy chatbots in a way that doesn鈥檛 favor individuals in certain demographic groups need a way to understand the risks their applications pose and the magnitude of potential issues. FairNow鈥檚 chatbot assessment methodology enables users to evaluate their models before they deploy and as part of ongoing monitoring.

Benefits to the organisation using the technique

Organisations attain high-fidelity bias evaluations of their models that reflect the ways in which their customers use the chatbot. Compared with existing chatbot bias benchmarks 鈥� which are often not specific enough to reflect actual usages 鈥� FairNow鈥檚 chatbot bias assessment methodology enables organisations to pinpoint specific issues with bias in relation to the chatbot鈥檚 intended and realized use.

皇冠体育app evaluation can be run at any point and does not require the organisation to share any protected data from customers or employees since the prompts are synthetically generated.

Limitations of the approach

皇冠体育app field of chatbot and LLM evaluations is emergent, and we鈥檙e committed to ongoing research and development to stay at the forefront of LLM bias testing. First, the field doesn鈥檛 yet fully understand the sensitivity of evaluation results to changes in testing procedures. Research shows that evaluation outcomes can change unexpectedly due to slight changes in the wording or style of the input prompt. Second, this evaluation is not comprehensive of all the different ways that a chatbot could display bias. 皇冠体育app evaluation currently tests for bias by gender and race, and does not yet test for bias in terms of other relevant factors like age. We鈥檙e committed to following the latest scientific literature on this topic and applying our own testing to reduce these limitations. Lastly, this bias assessment is focused on bias (and robustness of responses to individuals of different demographic groups), and is not designed to measure a chatbot鈥檚 safety or security posture.

Further links:

Further AI Assurance Information

• For more information about other techniques visit the Portfolio of AI Assurance Tools
• For more information on relevant standards visit the