Metraipolis › archive › dc_1f7b7ffca65b
Reversing Arrows in Large Language Models — arXiv:2608.03512
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03512
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:16:24.703Z
- SHA-256 of the archived text
bf90306ca4e8165489491c3181467b5f9d4c8cef0f96502d99e87cec192f5d4e- Stable URL of this page
https://metraipolis.com/documento/dc_1f7b7ffca65b
How to cite
Reversing Arrows in Large Language Models — arXiv:2608.03512 — arXiv (en), https://arxiv.org/abs/2608.03512 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1f7b7ffca65b (Metraipolis archive dc_1f7b7ffca65b, sha256 bf90306ca4e8165489491c3181467b5f9d4c8cef0f96502d99e87cec192f5d4e)
BibTeX
@misc{dc1f7b7ffca65b,
title = {Reversing Arrows in Large Language Models — arXiv:2608.03512},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03512},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1f7b7ffca65b; sha256 bf90306ca4e8165489491c3181467b5f9d4c8cef0f96502d99e87cec192f5d4e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03512. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) have achieved strong performance on text-to-knowledge graph generation and related tasks. Nevertheless, it is still unclear whether they accurately model the direction-dependent semantics of inverse relations, in which reversing the order of the arguments alters the meaning of a relation (e.g., \textit{mother} versus \textit{child}). To the best of our knowledge, this work presents the first systematic study of inverse relation directionality in LLMs, using a benchmark consisting of 5,457 instances spanning 27 distinct inverse relation labels. We evaluate five open-source LLMs under a multiple-choice prompting framework and further examine the influence of relation descriptions and entity representations by substituting the original entities with synthetic and masked entities. Our findings reveal systematic asymmetries in inverse relation classification across LLMs, indicate that relation descriptions do not consistently improve performance, and show that model performance can be sensitive to variations in entity representations.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03512 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:52.805Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).