Large LMs such as GPT-3 are powerful, but can commit mistakes that are obvious to humans. For example, GPT-3 would mistakenly interpret "What word is similar to good?" to mean a homophone, while the user intended a synonym. Our goal is to effectively correct such errors via user interactions with the system but without retraining, which will be prohibitively costly. We pair GPT-3 with a growing memory of recorded cases where the model misunderstood the user's intents, along with user feedback for clarification. Such a memory allows our system to produce enhanced prompts for any new query based on the user feedback for error correction on similar cases in the past. On four tasks (two lexical tasks, two advanced ethical reasoning tasks), we show how a (simulated) user can interactively teach a deployed GPT-3, substantially increasing its accuracy over the queries with different kinds of misunderstandings by the GPT-3. Our approach is a step towards the low-cost utility enhancement for very large pre-trained LMs. Code, data, and instructions to implement MEMPROMPT for a new task at https://www.memprompt.com/.
GPT Assisted Annotation of Rhetorical and Linguistic Features for Interpretable Propaganda Technique Detection in News Text
Technological University Dublin(都柏林理工大学);SFI Centre for Research Training in Machine Learning(SFI机器学习研究培训中心);School of Computer Science(计算机学院);Artificial Intelligence and Cognitive Load Research Lab(人工智能与认知负荷研究实验室)
Bayesian Optimization for Controlled Image Editing via LLMs
University of Edinburgh(爱丁堡大学);University of Manchester(曼彻斯特大学);University of Washington(华盛顿大学);Tsinghua University(清华大学);Skai Intelligence(Skai智能科技);University of Copenhagen(哥本哈根大学)