@inproceedings{li2025_110866,
  title = {Language Models Are Poor Learners of Directional Inference},
  author = {Li, Tianyi and Hosseini, Mohammad Javad and Weber, Sabine and Steedman, Mark},
  year = {2025},
  pages = {903–921},
  publisher = {Otto-Friedrich-Universität},
  address = {Bamberg},
  urn = {urn:nbn:de:bvb:473-irb-110866x},
  url = {https://fis.uni-bamberg.de/handle/uniba/110866},
  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}
}
