Miriam Anschütz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Miriam Anschütz has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Georg Groh
Technical University of Munich
2 shared publications - Georg Groh
School for Computation Information and Technology Technical University of Munich Germany
2 shared publications - Bartłomiej Jezierski
School for Computation, Information and Technology Technical University of Munich Germany
1 shared publication - Daniel Dyrda
Technical University of Munich Arcisstrasse 21 80333 Munich Germany
1 shared publication - Ekaterina Gikalo
School of Computation Information and Technology Technical University of Munich
1 shared publication - Ekaterina Lapshinova-Koltunski
University of Hildesheim
1 shared publication
Latest Publications
- Open Access
Diamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs
Recent research has demonstrated that large language models (LLMs) can support experts across various domains, including game design. In this study, we examine the utility of medium-sized LLMs, models that operate on consumer-grade hardware typically available in small studios or home environments. We began by identifying ten key aspects that contribute to a strong game concept and used ChatGPT to generate thirty sample game ideas. Three medium-sized LLMs, LLaMA 3.1, Qwen 2.5, and DeepSeek-R1, were then prompted to evaluate these ideas according to the previously identified aspects. A qualitative assessment by two researchers compared the models' outputs, revealing that DeepSeek-R1 produced the most consistently useful feedback, despite some variability in quality. To explore real-world applicability, we ran a pilot study with ten students enrolled in a storytelling course for game development. At the early stages of their own projects, students used our prompt and DeepSeek-R1 to refine their game concepts. The results indicate a positive reception: most participants rated the output as high quality and expressed interest in using such tools in their workflows. These findings suggest that current medium-sized LLMs can provide valuable feedback in early game design, though further refinement of prompting methods could improve consistency and overall effectiveness.
Open AccessDiamonds in the rough: Transforming SPARCs of imagination into a game concept by leveraging medium sized LLMs
Recent research has demonstrated that large language models (LLMs) can support experts across various domains, including game design. In this study, we examine the utility of medium-sized LLMs, models that operate on consumer-grade hardware typically available in small studios or home environments. We began by identifying ten key aspects that contribute to a strong game concept and used ChatGPT to generate thirty sample game ideas. Three medium-sized LLMs, LLaMA 3.1, Qwen 2.5, and DeepSeek-R1, were then prompted to evaluate these ideas according to the previously identified aspects. A qualitative assessment by two researchers compared the models' outputs, revealing that DeepSeek-R1 produced the most consistently useful feedback, despite some variability in quality. To explore real-world applicability, we ran a pilot study with ten students enrolled in a storytelling course for game development. At the early stages of their own projects, students used our prompt and DeepSeek-R1 to refine their game concepts. The results indicate a positive reception: most participants rated the output as high quality and expressed interest in using such tools in their workflows. These findings suggest that current medium-sized LLMs can provide valuable feedback in early game design, though further refinement of prompting methods could improve consistency and overall effectiveness.
- 29 July 2025
- Published by Springer Nature
- p. 57-71
Künstliche Intelligenz: Wie funktioniert KI für Einfache Sprache?
- 29 July 2025
- Published by Springer Nature
- p. 57-71
Künstliche Intelligenz: Wie funktioniert KI für Einfache Sprache?
- Open Access
Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
Large Language Models (LLMs) can provide accurate word definitions and explanations for any context. However, the scope of the definition changes for different target groups, like children or language learners. This is especially relevant for homonyms, words with multiple meanings, where oversimplification might risk information loss by omitting key senses, potentially misleading users who trust LLM outputs. We investigate how simplification impacts homonym definition quality across three target groups: Normal, Simple, and ELI5. Using two novel evaluation datasets spanning multiple languages, we test DeepSeek v3, Llama 4 Maverick, Qwen3-30B A3B, GPT-4o mini, and Llama 3.1 8B via LLM-as-Judge and human annotations. Our results show that simplification drastically degrades definition completeness by neglecting polysemy, increasing the risk of misunderstanding. Fine-tuning Llama 3.1 8B with Direct Preference Optimization substantially improves homonym response quality across all prompt types. These findings highlight the need to balance simplicity and completeness in educational NLP to ensure reliable, context-aware definitions for all learners.
Open AccessSimplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
Large Language Models (LLMs) can provide accurate word definitions and explanations for any context. However, the scope of the definition changes for different target groups, like children or language learners. This is especially relevant for homonyms, words with multiple meanings, where oversimplification might risk information loss by omitting key senses, potentially misleading users who trust LLM outputs. We investigate how simplification impacts homonym definition quality across three target groups: Normal, Simple, and ELI5. Using two novel evaluation datasets spanning multiple languages, we test DeepSeek v3, Llama 4 Maverick, Qwen3-30B A3B, GPT-4o mini, and Llama 3.1 8B via LLM-as-Judge and human annotations. Our results show that simplification drastically degrades definition completeness by neglecting polysemy, increasing the risk of misunderstanding. Fine-tuning Llama 3.1 8B with Direct Preference Optimization substantially improves homonym response quality across all prompt types. These findings highlight the need to balance simplicity and completeness in educational NLP to ensure reliable, context-aware definitions for all learners.
- Open Access
TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification
Hallucinations are one of the major problems of LLMs, hindering their trustworthiness and deployment to wider use cases. However, most of the research on hallucinations focuses on English data, neglecting the multilingual nature of LLMs. This paper describes our submission to the SemEval-2025 Task-3 - Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. We propose a two-part pipeline that combines retrieval-based fact verification against Wikipedia with a BERT-based system fine-tuned to identify common hallucination patterns. Our system achieves competitive results across all languages, reaching top-10 results in eight languages, including English. Moreover, it supports multiple languages beyond the fourteen covered by the shared task. This multilingual hallucination identifier can help to improve LLM outputs and their usefulness in the future.
Open AccessTUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification
Hallucinations are one of the major problems of LLMs, hindering their trustworthiness and deployment to wider use cases. However, most of the research on hallucinations focuses on English data, neglecting the multilingual nature of LLMs. This paper describes our submission to the SemEval-2025 Task-3 - Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. We propose a two-part pipeline that combines retrieval-based fact verification against Wikipedia with a BERT-based system fine-tuned to identify common hallucination patterns. Our system achieves competitive results across all languages, reaching top-10 results in eight languages, including English. Moreover, it supports multiple languages beyond the fourteen covered by the shared task. This multilingual hallucination identifier can help to improve LLM outputs and their usefulness in the future.
- Open Access
Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training
Automatic text simplification systems help to reduce textual information barriers on the internet. However, for languages other than English, only few parallel data to train these systems exists. We propose a two-step approach to overcome this data scarcity issue. First, we fine-tuned language models on a corpus of German Easy Language, a specific style of German. Then, we used these models as decoders in a sequence-to-sequence simplification task. We show that the language models adapt to the style characteristics of Easy Language and output more accessible texts. Moreover, with the style-specific pre-training, we reduced the number of trainable parameters in text simplification models. Hence, less parallel data is sufficient for training. Our results indicate that pre-training on unaligned data can reduce the required parallel data while improving the performance on downstream tasks.
Open AccessLanguage Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training
Automatic text simplification systems help to reduce textual information barriers on the internet. However, for languages other than English, only few parallel data to train these systems exists. We propose a two-step approach to overcome this data scarcity issue. First, we fine-tuned language models on a corpus of German Easy Language, a specific style of German. Then, we used these models as decoders in a sequence-to-sequence simplification task. We show that the language models adapt to the style characteristics of Easy Language and output more accessible texts. Moreover, with the style-specific pre-training, we reduced the number of trainable parameters in text simplification models. Hence, less parallel data is sufficient for training. Our results indicate that pre-training on unaligned data can reduce the required parallel data while improving the performance on downstream tasks.
- Open Access
Retrieving Users' Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis
People post their opinions and experiences on social media, yielding rich databases of end-users' sentiments. This paper shows to what extent machine learning can analyze and structure these databases. An automated data analysis pipeline is deployed to provide insights into user-generated content for researchers in other domains. First, the domain expert can select an image and a term of interest. Then, the pipeline uses image retrieval to find all images showing similar content and applies aspect-based sentiment analysis to outline users' opinions about the selected term. As part of an interdisciplinary project between architecture and computer science researchers, an empirical study of Hamburg's Elbphilharmonie was conveyed. Therefore, we selected 300 thousand posts with the hashtag \enquote{\texttt{hamburg}} from the platform Flickr. Image retrieval methods generated a subset of slightly more than 1.5 thousand images displaying the Elbphilharmonie. We found that these posts mainly convey a neutral or positive sentiment towards it. With this pipeline, we suggest a new semantic computing method that offers novel insights into end-users opinions, e.g., for architecture domain experts.
Open AccessRetrieving Users' Opinions on Social Media with Multimodal Aspect-Based Sentiment Analysis
People post their opinions and experiences on social media, yielding rich databases of end-users' sentiments. This paper shows to what extent machine learning can analyze and structure these databases. An automated data analysis pipeline is deployed to provide insights into user-generated content for researchers in other domains. First, the domain expert can select an image and a term of interest. Then, the pipeline uses image retrieval to find all images showing similar content and applies aspect-based sentiment analysis to outline users' opinions about the selected term. As part of an interdisciplinary project between architecture and computer science researchers, an empirical study of Hamburg's Elbphilharmonie was conveyed. Therefore, we selected 300 thousand posts with the hashtag \enquote{\texttt{hamburg}} from the platform Flickr. Image retrieval methods generated a subset of slightly more than 1.5 thousand images displaying the Elbphilharmonie. We found that these posts mainly convey a neutral or positive sentiment towards it. With this pipeline, we suggest a new semantic computing method that offers novel insights into end-users opinions, e.g., for architecture domain experts.