Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility

Xiaomeng Zhu, Zhenghao Zhou, Simon Charlow, Robert Frank


Abstract
We present a hierarchy of natural language understanding abilities and argue for the importance of moving beyond assessments of understanding at the lexical and sentence levels to the discourse level. We propose the task of anaphora accessibility as a diagnostic for assessing discourse understanding, and to this end, present an evaluation dataset inspired by theoretical research in dynamic semantics. We evaluate human and LLM performance on our dataset and find that LLMs and humans align on some tasks and diverge on others. Such divergence can be explained by LLMs’ reliance on specific lexical items during language comprehension, in contrast to human sensitivity to structural abstractions.
Anthology ID:
2025.acl-long.432
Volume:
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2025
Address:
Vienna, Austria
Editors:
Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8824–8842
Language:
URL:
https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.432/
DOI:
Bibkey:
Cite (ACL):
Xiaomeng Zhu, Zhenghao Zhou, Simon Charlow, and Robert Frank. 2025. Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8824–8842, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility (Zhu et al., ACL 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.432.pdf