3 papers
cs.CL2023
Explanation-based Finetuning Makes Models More Robust to Spurious Cues
Josh Magnus Ludan, Yixuan Meng, Tai Nguyen +4
Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on o…
cs.CL2023
Representation Of Lexical Stylistic Features In Language Models' Embedding Space
Qing Lyu, Marianna Apidianaki, Chris Callison-Burch
The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy, polysemy) as well as abstrac…
cs.CL2021
Is "My Favorite New Movie" My Favorite Movie? Probing the Understanding of Recursive Noun Phrases
Qing Lyu, Hua Zheng, Daoxin Li +3
Recursive noun phrases (NPs) have interesting semantic properties. For example, "my favorite new movie" is not necessarily my favorite movie, whereas "my new favorite movie" is. Th…