97 citations · 109 across the 4 of their papers we have counts for
3 papers · 1 filter
The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
Sander Schulhoff, Michael Ilie, Nishant Balepur +28
Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these syst…
Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong
Chenglei Si, Navita Goyal, Sherry Tongshuang Wu +4
Large Language Models (LLMs) are increasingly used for accessing information on the web. Their truthfulness and factuality are thus of great interest. To help users make the right…
Re-Examining Calibration: The Case of Question Answering
Chenglei Si, Chen Zhao, Sewon Min +1
For users to trust model predictions, they need to understand model outputs, particularly their confidence - calibration aims to adjust (calibrate) models' confidence to match expe…