Papers by Sander Schulhoff
Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition (2023.emnlp-main)
Copied to clipboard
Sander Schulhoff, Jeremy Pinto, Anaum Khan, Louis-François Bouchard, Chenglei Si, Svetlina Anati, Valen Tagliabue, Anson Kost, Christopher Carnahan, Jordan Boyd-Graber
| Challenge: | Large Language Models are increasingly being deployed in interactive contexts that involve direct user engagement. |
| Approach: | They run a global prompt hacking competition to encourage research on prompt hacks . they elicit 600K+ adversarial prompts against three state-of-the-art LLMs based on a dataset . |
| Outcome: | The results of the competition show that current LLMs can be manipulated via prompt hacking . the competition elicits 600K+ adversarial prompts against three state-of-the-art LLM models . |
GPT Deciphering Fedspeak: Quantifying Dissent Among Hawks and Doves (2023.findings-emnlp)
Copied to clipboard
| Challenge: | We use GPT-4 to quantify dissent among members on the topic of inflation . transcripts and minutes reflect the diversity of member views in a way that is lost or omitted from the public statements. |
| Approach: | They use transcripts and minutes to quantify dissent among FOMC members . they find that transcripts reflect diversity of member views in a way that is lost or omitted . |
| Outcome: | The proposed method better captures extremes, which mirror human annotations, and suggests that Large Language Models can avoid noise in this nuanced context. |