← Search

Jinsol Park

2 accepted papers

2023

PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering

EMNLP 2023short main

Information-seeking questions in long-form question answering (LFQA) often prove misleading due to ambiguity or false presupposition in the question. While many existing approaches handle misleading questions, they are tailored to limited questions, which are insufficient in a real-world setting wit…

Cited by 0SourceScholar
2023

Two Examples are Better than One: Context Regularization for Gradient-based Prompt Tuning

ACL 2023findings

Prompting has gained tremendous attention as an efficient method for the adaptation of large-scale language models. However, prompts often act against human intuition and report unstable performances, which has motivated methods that automatically find effective prompts. One popular approach is grad…

Cited by 1SourcePDFScholar