{"slug": "do-llms-fail-in-bridging-generation", "title": "Do LLMs fail in bridging generation?", "summary": "Natalia Skachkova, Simon Ostermann, Josef van Genabith, and Bernd Kiefer found that large language models mostly fail to generate bridging relations reliably, according to a study published in the Journal for Language Technology and Computational Linguistics, Vol. 38 No. 2, pages 77–95, in July 2025. The authors ran two tasks — generating texts containing bridging and filling in missing bridging spans — and reported that in most cases the models could not use bridging knowledge effectively.", "body_md": "##### Abstract\n\nIn this work we investigate whether large language models (LLMs) ‘understand’ bridging relations and can use this knowledge effectively. We present the results obtained from two tasks: generation of texts containing bridging and filling in missing bridging spans. We show that in most of the cases LLMs fail to generate bridging in a reliable way.\n- Anthology ID:\n- 2025.jlcl-2.5\n- Volume:\n- [Journal for Language Technology and Computational Linguistics, Vol. 38 No. 2: LLM Fails - Failed experiments with generative AI and what we can learn from them](https://aclanthology.org/volumes/2025.jlcl-2/)\n- Month:\n- July\n- Year:\n- 2025\n- Address:\n- Editors:\n- [Ngoc Duyen Tanja Tu](https://aclanthology.org/people/ngoc-duyen-tanja-tu/unverified/) ,[Annelen Brunner](https://aclanthology.org/people/annelen-brunner/unverified/) ,[Christian Lang](https://aclanthology.org/people/christian-lang/unverified/)\n- Venue:\n- [JLCL](https://aclanthology.org/venues/jlcl/)\n- SIG:\n- Publisher:\n- German Society for Computational Linguistics and Language Technology\n- Note:\n- Pages:\n- 77–95\n- Language:\n- URL:\n- [https://aclanthology.org/2025.jlcl-2.5/](https://aclanthology.org/2025.jlcl-2.5/)\n- DOI:\n- [10.21248/jlcl.38.2025.286](https://doi.org/10.21248/jlcl.38.2025.286)\n- Cite (ACL):\n- Natalia Skachkova, Simon Ostermann, Josef van Genabith, and Bernd Kiefer. 2025. [Do LLMs fail in bridging generation?](https://aclanthology.org/2025.jlcl-2.5/) .*Journal for Language Technology and Computational Linguistics* , 38(2):77–95.\n- Cite (Informal):\n- [Do LLMs fail in bridging generation?](https://aclanthology.org/2025.jlcl-2.5/) (Skachkova et al., JLCL 2025)\n- PDF:\n- [https://aclanthology.org/2025.jlcl-2.5.pdf](https://aclanthology.org/2025.jlcl-2.5.pdf)", "url": "https://wpnews.pro/news/do-llms-fail-in-bridging-generation", "canonical_source": "https://aclanthology.org/2025.jlcl-2.5/", "published_at": "2026-10-14 00:00:00+00:00", "updated_at": "2026-10-16 12:47:23.182542+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research", "artificial-intelligence"], "entities": ["Natalia Skachkova", "Simon Ostermann", "Josef van Genabith", "Bernd Kiefer", "Journal for Language Technology and Computational Linguistics", "German Society for Computational Linguistics and Language Technology"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/do-llms-fail-in-bridging-generation", "markdown": "https://wpnews.pro/news/do-llms-fail-in-bridging-generation.md", "text": "https://wpnews.pro/news/do-llms-fail-in-bridging-generation.txt", "jsonld": "https://wpnews.pro/news/do-llms-fail-in-bridging-generation.jsonld"}}