Vol. 38 No. 2 (2025): LLM fails – Failed experiments with generative AI and what we can learn from them

Guest editors: Ngoc Duyen Tanja Tu, Annelen Brunner and Christian Lang

Published: 2025-07-08

Full Issue

PDF

Editorial

Editorial

Ngoc Duyen Tanja Tu, Annelen Brunner, Christian Lang
- PDF

Research articles

Exploring the Limits of LLMs for German Text Classification: Prompting and Fine-tuning Strategies Across Small and Medium-sized Datasets

Elena Leitner, Georg Rehm

1-12
- PDF
Large language models for terminology work: A question of the right prompt?

Barbara Heinisch

13-30
- PDF
A Study of Errors in the Output of Large Language Models for Domain-Specific Few-Shot Named Entity Recognition

Elena Volkanovska

31-42
- PDF
GPT makes a poor AMR parser

Yanming Li, Meaghan Fowlie

43-76
- PDF
Do LLMs fail in bridging generation?

Natalia Skachkova, Simon Ostermann, Josef van Genabith, Bernd Kiefer

77-95
- PDF
The Struggles of Large Language Models with Zero- and Few-Shot (Extended) Metaphor Detection

Sebastian Reimann, Tatjana Scheffler

97-109
- PDF
Pictorial constituents & the metalinguistic performance of LLMs

John David Storment

111-124
- PDF
Political Bias in LLMs: Unaligned Moral Values in Agent-centric Simulations

Simon Münker

125-138
- PDF