Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently
Abstract: Recent zero-shot evaluations have highlighted important limitations in the abilities of language models (LMs) to perform meaning extraction. However, it is now well known that LMs can demonstrate radical improvements in the presence of experimental contexts such as in-context examples and instructions. How well does this translate to previously studied meaning-sensitive tasks? We present a case-study on the extent to which experimental contexts can improve LMs' robustness in performing property inheritance---predicting semantic properties of novel concepts, a task that they have been previously shown to fail on. Upon carefully controlling the nature of the in-context examples and the instructions, our work reveals that they can indeed lead to non-trivial property inheritance behavior in LMs. However, this ability is inconsistent: with a minimal reformulation of the task, some LMs were found to pick up on shallow, non-semantic heuristics from their inputs, suggesting that the computational principles of semantic property inference are yet to be mastered by LMs. Our code will be available at (future-url)
Paper Type: Short
Research Area: Interpretability and Analysis of Models for NLP
Research Area Keywords: data shortcuts/artifacts; robustness
Contribution Types: Model analysis & interpretability
Languages Studied: English
Section 2 Permission To Publish Peer Reviewers Content Agreement: Authors grant permission for ACL to publish peer reviewers' content
Submission Number: 59
Loading