OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs
This addresses the issue of bias transparency in AI for users and researchers, offering a novel approach rather than debiasing, but it is incremental as it builds on existing instruction-tuning methods.
The paper tackles the problem of inherent biases in instruction-tuned LLMs by proposing OpinionGPT, a web demo that makes biases explicit and transparent, allowing users to compare responses fine-tuned on text from 11 different demographic biases.
Instruction-tuned Large Language Models (LLMs) have recently showcased remarkable ability to generate fitting responses to natural language instructions. However, an open research question concerns the inherent biases of trained models and their responses. For instance, if the data used to tune an LLM is dominantly written by persons with a specific political bias, we might expect generated answers to share this bias. Current research work seeks to de-bias such models, or suppress potentially biased answers. With this demonstration, we take a different view on biases in instruction-tuning: Rather than aiming to suppress them, we aim to make them explicit and transparent. To this end, we present OpinionGPT, a web demo in which users can ask questions and select all biases they wish to investigate. The demo will answer this question using a model fine-tuned on text representing each of the selected biases, allowing side-by-side comparison. To train the underlying model, we identified 11 different biases (political, geographic, gender, age) and derived an instruction-tuning corpus in which each answer was written by members of one of these demographics. This paper presents OpinionGPT, illustrates how we trained the bias-aware model and showcases the web application (available at https://opiniongpt.informatik.hu-berlin.de).