TY - JOUR A1 - Lukas, Wolfang A1 - Brehm, David A1 - Durdel, Patrick A1 - Papart, Sönke A1 - Kreuter, Sara A1 - Weinbach, Donata A1 - Pfeifer, Lena A1 - Assadsolimani, Jasmin A1 - Wagner, Alexander ED - Lukas, Wolfgang ED - Nies, Martin T1 - Zeichen des Fremden BT - und ihre Metaisierung in ästhetischen Diskursen der Gegenwart N2 - Zuerst erschienen auf: https://www.kultursemiotik.com/forschung/publikationen/schriftenreihe-online/ Inhalt Zeichen des Fremden Einleitung Wolfgang Lukas / Martin Nies Wessen Rettung? Geflüchtete Figuren, Sinnproduktion und implizite Poetik in Jenny Erpenbecks 'Gehen, ging, gegangen' und Bodo Kirchhoffs 'Widerfahrnis' David Brehm Der falsche Fremde Auto- und metafiktionale Reflexionen von Identität und Ethnizität in Abbas Khiders 'Der falsche Inder' Sönke Parpart „Ich habe kein Bild mehr von mir“ (De-)Konstruktion von Identität und Fremdheit in Jenny Erpenbecks 'Gehen, ging, gegangen' (2015) und Olga Grjasnowas 'Gott ist nicht schüchtern' (2018) Sara Kreuter Verfinsterungen des Eigenen Konstruktionen des Anderen in Wolfram Lotz’ 'Die lächerliche Finsternis' Patrick Durdel Die vertraute Fremdheit der Anthropophagie Franzobels 'Floß der Medusa' (2017) Donata Weinbach Intimate Weavings Tracing Urban and Corporeal Others in Sinéad Morrissey’s Poetry Lena Pfeifer Make America en vogue again Die Konstruktion einer nationalen Identität in der US-amerikanischen Vogue nach dem Trump-Wahlsieg Jasmin Assadsolimani Schweiz / Haiti / NEW WORLD PLAZA Individualgeschichte und Universalgeschichte in Dorothee Elmigers 'Aus der Zuckerfabrik' Alexander Wagner T3 - Schriften zur Kultur- und Mediensemiotik | Online - 9 KW - Einwanderung KW - Kulturelle Identität KW - Fremdheit KW - Gegenwartsliteratur Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:101:1-2023081602100461706063 VL - 2023 IS - 9 ER - TY - JOUR A1 - Zubaer, Abdullah Al A1 - Granitzer, Michael A1 - Mitrović, Jelena T1 - Performance analysis of large language models in the domain of legal argument mining JF - Frontiers in Artificial Intelligence N2 - Generative pre-trained transformers (GPT) have recently demonstrated excellent performance in various natural language tasks. The development of ChatGPT and the recently released GPT-4 model has shown competence in solving complex and higher-order reasoning tasks without further training or fine-tuning. However, the applicability and strength of these models in classifying legal texts in the context of argument mining are yet to be realized and have not been tested thoroughly. In this study, we investigate the effectiveness of GPT-like models, specifically GPT-3.5 and GPT-4, for argument mining via prompting. We closely study the model's performance considering diverse prompt formulation and example selection in the prompt via semantic search using state-of-the-art embedding models from OpenAI and sentence transformers. We primarily concentrate on the argument component classification task on the legal corpus from the European Court of Human Rights. To address these models' inherent non-deterministic nature and make our result statistically sound, we conducted 5-fold cross-validation on the test set. Our experiments demonstrate, quite surprisingly, that relatively small domain-specific models outperform GPT 3.5 and GPT-4 in the F1-score for premise and conclusion classes, with 1.9% and 12% improvements, respectively. We hypothesize that the performance drop indirectly reflects the complexity of the structure in the dataset, which we verify through prompt and data analysis. Nevertheless, our results demonstrate a noteworthy variation in the performance of GPT models based on prompt formulation. We observe comparable performance between the two embedding models, with a slight improvement in the local model's ability for prompt selection. This suggests that local models are as semantically rich as the embeddings from the OpenAI model. Our results indicate that the structure of prompts significantly impacts the performance of GPT models and should be considered when designing them. KW - natural language processing (NLP) KW - argument mining KW - legal data KW - European Court of Human Rights (ECHR) KW - sequence classification KW - GPT-4 KW - ChatGPT KW - large language models Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:739-opus4-18326 SN - 2624-8212 VL - 2023 IS - 6 PB - Frontiers CY - Lausanne ER - TY - JOUR A1 - Hackl, Veronika A1 - Müller, Alexandra Elena A1 - Granitzer, Michael A1 - Sailer, Maximilian T1 - Is GPT-4 a reliable rater? Evaluating consistency in GPT-4's text ratings JF - Frontiers in Education N2 - This study reports the Intraclass Correlation Coefficients of feedback ratings produced by OpenAI's GPT-4, a large language model (LLM), across various iterations, time frames, and stylistic variations. The model was used to rate responses to tasks related to macroeconomics in higher education (HE), based on their content and style. Statistical analysis was performed to determine the absolute agreement and consistency of ratings in all iterations, and the correlation between the ratings in terms of content and style. The findings revealed high interrater reliability, with ICC scores ranging from 0.94 to 0.99 for different time periods, indicating that GPT-4 is capable of producing consistent ratings. The prompt used in this study is also presented and explained. KW - artificial intelligence KW - GPT-4 KW - large language model KW - prompt engineering KW - feedback KW - higher education Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:739-opus4-18348 SN - 2504-284X VL - 2023 IS - 8 PB - Frontiers CY - Lausanne ER -