most citedEnhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2022★ 1 cited

Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference

Eric Mitchell, Joseph J. Noh, Siyan Li +5

While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs. For example, a state-of-the-art Macaw question-answering…