Six years ago today, Joaquin Oliver was killed in a hallway outside his Florida classroom, one of 17 students and staff murdered in the worst high school shooting in the US. On Wednesday, lawmakers in Washington DC will hear his voice, recreated by artificial intelligence, in phone calls demanding to know why they've done nothing to tackle the plague of gun violence. "It's been six years and you've done nothing. Not a thing to stop all the shootings that have happened since," the message from Oliver, who was 17 when he died in the 2018 Valentine's Day's tragedy at Parkland's Marjory Stoneman Douglas high school, says. "I'm back today because my parents used AI to recreate my voice to call you. Other victims like me will be calling too, again and again, to demand action. How many calls will it take for you to care? How many dead voices will you hear before you finally listen?"

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).

In the United States, it seems we never have to go more than a few weeks without hearing about another mass shooting. With each new incident comes renewed calls to strengthen gun control laws, expand federal background checks, and get rid of assault rifles. Though the opposing faction promptly dismisses each appeal by citing 2nd Amendment rights, other discussions of practicality often emerge. Specifically, the efficacy of such laws is often called into question. How do we know which laws work and which ones don't?