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

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 Ngoc Duyen Tanja Tu editor Annelen Brunner editor Christian Lang editor monographic 2025-07 German Society for Computational Linguistics and Language Technology text book jlcl-2025-2 https://aclanthology.org/2025.jlcl-2.0/ Exploring the Limits of LLMs for German Text Classification: Prompting and Fine-tuning Strategies Across Small and Medium-sized Datasets Elena Leitner author Georg Rehm author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal leitner-rehm-2025-exploring 10.21248/jlcl.38.2025.277 https://aclanthology.org/2025.jlcl-2.1/ 2025-07 38 2 1 12 Large language models for terminology work: A question of the right prompt? Barbara Heinisch author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal heinisch-2025-large 10.21248/jlcl.38.2025.280 https://aclanthology.org/2025.jlcl-2.2/ 2025-07 38 2 13 30 A Study of Errors in the Output of Large Language Models for Domain-Specific Few-Shot Named Entity Recognition Elena Volkanovska author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal volkanovska-2025-study 10.21248/jlcl.38.2025.281 https://aclanthology.org/2025.jlcl-2.3/ 2025-07 38 2 31 42 GPT makes a poor AMR parser Yanming Li author Meaghan Fowlie author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal li-fowlie-2025-gpt 10.21248/jlcl.38.2025.285 https://aclanthology.org/2025.jlcl-2.4/ 2025-07 38 2 43 76 Do LLMs fail in bridging generation? Natalia Skachkova author Simon Ostermann author Josef van Genabith author Bernd Kiefer author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal skachkova-etal-2025-llms 10.21248/jlcl.38.2025.286 https://aclanthology.org/2025.jlcl-2.5/ 2025-07 38 2 77 95 The Struggles of Large Language Models with Zero- and Few-Shot (Extended) Metaphor Detection Sebastian Reimann author Tatjana Scheffler author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal reimann-scheffler-2025-struggles 10.21248/jlcl.38.2025.287 https://aclanthology.org/2025.jlcl-2.6/ 2025-07 38 2 97 109 Pictorial constituents & the metalinguistic performance of LLMs John David Storment author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal storment-2025-pictorial 10.21248/jlcl.38.2025.295 https://aclanthology.org/2025.jlcl-2.7/ 2025-07 38 2 111 124 Political Bias in LLMs: Unaligned Moral Values in Agent-centric Simulations Simon Münker author 2025-07 text journal article Journal for Language Technology and Computational Linguistics continuing German Society for Computational Linguistics and Language Technology periodical academic journal munker-2025-political 10.21248/jlcl.38.2025.289 https://aclanthology.org/2025.jlcl-2.8/ 2025-07 38 2 125 138