@inproceedings{li2022_97222,
  title = {Language Models Are Poor Learners of Directional Inference},
  author = {Li, Tianyi and Hosseini, Mohammad Javad and Weber, Sabine and Steedman, Mark},
  year = {2022},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2022},
  pages = {903–921},
  publisher = {Association for Computational Linguistics},
  doi = {10.18653/v1/2022.findings-emnlp.64},
  url = {https://fis.uni-bamberg.de/handle/uniba/97222},
  language = {eng},
  abstract = {We examine LMs’ competence of directional predicate entailments by supervised fine-tuning with prompts. Our analysis shows that contrary to their apparent success on standard NLI, LMs show limited ability to learn such directional inference; moreover, existing datasets fail to test directionality, and/or are infested by artefacts that can be learnt as proxy for entailments, yielding over-optimistic results. In response, we present BoOQA (Boolean Open QA), a robust multi-lingual evaluation benchmark for directional predicate entailments, extrinsic to existing training sets. On BoOQA, we establish baselines and show evidence of existing LM-prompting models being incompetent directional entailment learners, in contrast to entailment graphs, however limited by sparsity.},
  keywords = {Language Models}
}
