Tim Schlippe

Lorenz Mindner, Tim Schlippe, Kristina Schaaff

Recently, generative AIs like ChatGPT have become available to the wide public. These tools can for instance be used by students to generate essays or whole theses. But how does a teacher know whether a text is written by a student or an AI? In our work, we explore traditional and new features to (1) detect text generated by AI from scratch and (2) text rephrased by AI. Since we found that classification is more difficult when the AI has been instructed to create the text in a way that a human would not recognize that it was generated by an AI, we also investigate this more advanced case. For our experiments, we produced a new text corpus covering 10 school topics. Our best systems to classify basic and advanced human-generated/AI-generated texts have F1-scores of over 96%. Our best systems for classifying basic and advanced human-generated/AI-rephrased texts have F1-scores of more than 78%. The systems use a combination of perplexity, semantic, list lookup, error-based, readability, AI feedback, and text vector features. Our results show that the new features substantially help to improve the performance of many classifiers. Our best basic text rephrasing detection system even outperforms GPTZero by 183.8% relative in F1-score.

Kristina Schaaff, Caroline Reinig, Tim Schlippe

Empathy is often understood as the ability to share and understand another individual's state of mind or emotion. With the increasing use of chatbots in various domains, e.g., children seeking help with homework, individuals looking for medical advice, and people using the chatbot as a daily source of everyday companionship, the importance of empathy in human-computer interaction has become more apparent. Therefore, our study investigates the extent to which ChatGPT based on GPT-3.5 can exhibit empathetic responses and emotional expressions. We analyzed the following three aspects: (1) understanding and expressing emotions, (2) parallel emotional response, and (3) empathic personality. Thus, we not only evaluate ChatGPT on various empathy aspects and compare it with human behavior but also show a possible way to analyze the empathy of chatbots in general. Our results show, that in 91.7% of the cases, ChatGPT was able to correctly identify emotions and produces appropriate answers. In conversations, ChatGPT reacted with a parallel emotion in 70.7% of cases. The empathic capabilities of ChatGPT were evaluated using a set of five questionnaires covering different aspects of empathy. Even though the results show, that the scores of ChatGPT are still worse than the average of healthy humans, it scores better than people who have been diagnosed with Asperger syndrome / high-functioning autism.

Adrian Ryser, Florian Allwein, Tim Schlippe

Hallucinations are outputs by Large Language Models (LLMs) that are factually incorrect yet appear plausible [1]. This paper investigates how such hallucinations influence users' trust in LLMs and users' interaction with LLMs. To explore this in everyday use, we conducted a qualitative study with 192 participants. Our findings show that hallucinations do not result in blanket mistrust but instead lead to context-sensitive trust calibration. Building on the calibrated trust model by Lee & See [2] and Afroogh et al.'s trust-related factors [3], we confirm expectancy [3], [4], prior experience [3], [4], [5], and user expertise & domain knowledge [3], [4] as userrelated (human) trust factors, and identify intuition as an additional factor relevant for hallucination detection. Additionally, we found that trust dynamics are further influenced by contextual factors, particularly perceived risk [3] and decision stakes [6]. Consequently, we validate the recursive trust calibration process proposed by Blöbaum [7] and extend it by including intuition as a user-related trust factor. Based on these insights, we propose practical recommendations for responsible and reflective LLM use.

Christopher Goetze, Tim Schlippe, Daniel Lakey

Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.

Michael Marketsmüller, Simon Martin, Tim Schlippe

Enterprise systems increasingly require natural language interfaces that can translate user requests into structured operations such as SQL queries and REST API calls. While large language models (LLMs) show promise for code generation [Chen et al., 2021; Huynh and Lin, 2025], their effectiveness in domain-specific enterprise contexts remains underexplored, particularly when both retrieval and modification tasks must be handled jointly. This paper presents a comprehensive evaluation of three retrieval-augmented generation (RAG) variants [Lewis et al., 2021] -- standard RAG, Self-RAG [Asai et al., 2024], and CoRAG [Wang et al., 2025] -- across SQL query generation, REST API call generation, and a combined task requiring dynamic task classification. Using SAP Transactional Banking as a realistic enterprise use case, we construct a novel test dataset covering both modalities and evaluate 18 experimental configurations under database-only, API-only, and hybrid documentation contexts. Results demonstrate that RAG is essential: Without retrieval, exact match accuracy is 0% across all tasks, whereas retrieval yields substantial gains in execution accuracy (up to 79.30%) and component match accuracy (up to 78.86%). Critically, CoRAG proves most robust in hybrid documentation settings, achieving statistically significant improvements in the combined task (10.29% exact match vs. 7.45% for standard RAG), driven primarily by superior SQL generation performance (15.32% vs. 11.56%). Our findings establish retrieval-policy design as a key determinant of production-grade natural language interfaces, showing that iterative query decomposition outperforms both top-k retrieval and binary relevance filtering under documentation heterogeneity.

Kristina Schaaff, Tim Schlippe, Lorenz Mindner

In this paper we analyze features to classify human- and AI-generated text for English, French, German and Spanish and compare them across languages. We investigate two scenarios: (1) The detection of text generated by AI from scratch, and (2) the detection of text rephrased by AI. For training and testing the classifiers in this multilingual setting, we created a new text corpus covering 10 topics for each language. For the detection of AI-generated text, the combination of all proposed features performs best, indicating that our features are portable to other related languages: The F1-scores are close with 99% for Spanish, 98% for English, 97% for German and 95% for French. For the detection of AI-rephrased text, the systems with all features outperform systems with other features in many cases, but using only document features performs best for German (72%) and Spanish (86%) and only text vector features leads to best results for English (78%).

Julia Wagner, Tim Schlippe

In recent years, AI systems in the medical domain have advanced significantly. However, despite outperforming humans, they are rarely used in practice since it is often not clear how they make their decisions. Optimal explanation and visualization of the decision process are often lacking. Therefore, we conducted a comparative user-centric analysis of the latest state-of-the-art textual, visual and multimodal explainable artificial intelligence (XAI) methods for medical image diagnosis. Our survey of 33 physicians showed that 88% agree that it is important that AI explains the diagnosis -- 64% even strongly agree. A combination of bounding box and report is rated better than the other tested XAI methods in the evaluated aspects understandability, completeness, speed, and applicability. We even tested the potential negative impact of false AI-based medical image diagnoses and found that 50% of the participants trusted false AI diagnoses over all tested XAI methods.

Koena Ronny Mabokela, Tim Schlippe, Mpho Raborife et al.

Sentiment analysis is a helpful task to automatically analyse opinions and emotions on various topics in areas such as AI for Social Good, AI in Education or marketing. While many of the sentiment analysis systems are developed for English, many African languages are classified as low-resource languages due to the lack of digital language resources like text labelled with corresponding sentiment classes. One reason for that is that manually labelling text data is time-consuming and expensive. Consequently, automatic and rapid processes are needed to reduce the manual effort as much as possible making the labelling process as efficient as possible. In this paper, we present and analyze an automatic language-independent sentiment labelling method that leverages information from sentiment-bearing emojis and words. Our experiments are conducted with tweets in the languages English, Sepedi and Setswana from SAfriSenti, a multilingual sentiment corpus for South African languages. We show that our sentiment labelling approach is able to label the English tweets with an accuracy of 66%, the Sepedi tweets with 69%, and the Setswana tweets with 63%, so that on average only 34% of the automatically generated labels remain to be corrected.

Koena Ronny Mabokela, Tim Schlippe, Matthias Wölfel

Sentiment analysis can aid in understanding people's opinions and emotions on social issues. In multilingual communities sentiment analysis systems can be used to quickly identify social challenges in social media posts, enabling government departments to detect and address these issues more precisely and effectively. Recently, large-language models (LLMs) have become available to the wide public and initial analyses have shown that they exhibit magnificent zero-shot sentiment analysis abilities in English. However, there is no work that has investigated to leverage LLMs for sentiment analysis on social media posts in South African languages and detect social challenges. Consequently, in this work, we analyse the zero-shot performance of the state-of-the-art LLMs GPT-3.5, GPT-4, LlaMa 2, PaLM 2, and Dolly 2 to investigate the sentiment polarities of the 10 most emerging topics in English, Sepedi and Setswana social media posts that fall within the jurisdictional areas of 10 South African government departments. Our results demonstrate that there are big differences between the various LLMs, topics, and languages. In addition, we show that a fusion of the outcomes of different LLMs provides large gains in sentiment classification performance with sentiment classification errors below 1%. Consequently, it is now feasible to provide systems that generate reliable information about sentiment analysis to detect social challenges and draw conclusions about possible needs for actions on specific topics and within different language groups.

Tim Schlippe, Matthias Wölfel, Koena Ronny Mabokela

This study investigates how cultural proximity affects the ability to detect AI-generated fake news by comparing South African participants with those from other nationalities. As large language models increasingly enable the creation of sophisticated fake news, understanding human detection capabilities becomes crucial, particularly across different cultural contexts. We conducted a survey where 89 participants (56 South Africans, 33 from other nationalities) evaluated 10 true South African news articles and 10 AI-generated fake versions. Results reveal an asymmetric pattern: South Africans demonstrated superior performance in detecting true news about their country (40% deviation from ideal rating) compared to other participants (52%), but performed worse at identifying fake news (62% vs. 55%). This difference may reflect South Africans' higher overall trust in news sources. Our analysis further shows that South Africans relied more on content knowledge and contextual understanding when judging credibility, while participants from other countries emphasised formal linguistic features such as grammar and structure. Overall, the deviation from ideal rating was similar between groups (51% vs. 53%), suggesting that cultural familiarity appears to aid verification of authentic information but may also introduce bias when evaluating fabricated content. These insights contribute to understanding cross-cultural dimensions of misinformation detection and inform strategies for combating AI-generated fake news in increasingly globalised information ecosystems where content crosses cultural and geographical boundaries.

Thorsten Fröhlich, Tim Schlippe

The evaluation of academic theses is a cornerstone of higher education, ensuring rigor and integrity. Traditional methods, though effective, are time-consuming and subject to evaluator variability. This paper presents RubiSCoT, an AI-supported framework designed to enhance thesis evaluation from proposal to final submission. Using advanced natural language processing techniques, including large language models, retrieval-augmented generation, and structured chain-of-thought prompting, RubiSCoT offers a consistent, scalable solution. The framework includes preliminary assessments, multidimensional assessments, content extraction, rubric-based scoring, and detailed reporting. We present the design and implementation of RubiSCoT, discussing its potential to optimize academic assessment processes through consistent, scalable, and transparent evaluation.

Rui A. Pimenta, Tim Schlippe, Kristina Schaaff

We investigate consciousness-like behaviors in Large Language Models (LLMs) using the Maze Test, challenging models to navigate mazes from a first-person perspective. This test simultaneously probes spatial awareness, perspective-taking, goal-directed behavior, and temporal sequencing-key consciousness-associated characteristics. After synthesizing consciousness theories into 13 essential characteristics, we evaluated 12 leading LLMs across zero-shot, one-shot, and few-shot learning scenarios. Results showed reasoning-capable LLMs consistently outperforming standard versions, with Gemini 2.0 Pro achieving 52.9% Complete Path Accuracy and DeepSeek-R1 reaching 80.5% Partial Path Accuracy. The gap between these metrics indicates LLMs struggle to maintain coherent self-models throughout solutions -- a fundamental consciousness aspect. While LLMs show progress in consciousness-related behaviors through reasoning mechanisms, they lack the integrated, persistent self-awareness characteristic of consciousness.

Daniel Lakey, Tim Schlippe

Spacecraft operations are highly critical, demanding impeccable reliability and safety. Ensuring the optimal performance of a spacecraft requires the early detection and mitigation of anomalies, which could otherwise result in unit or mission failures. With the advent of deep learning, a surge of interest has been seen in leveraging these sophisticated algorithms for anomaly detection in space operations. This study aims to compare the efficacy of various deep learning architectures in detecting anomalies in spacecraft data. The deep learning models under investigation include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, and Transformer-based architectures. Each of these models was trained and validated using a comprehensive dataset sourced from multiple spacecraft missions, encompassing diverse operational scenarios and anomaly types. Initial results indicate that while CNNs excel in identifying spatial patterns and may be effective for some classes of spacecraft data, LSTMs and RNNs show a marked proficiency in capturing temporal anomalies seen in time-series spacecraft telemetry. The Transformer-based architectures, given their ability to focus on both local and global contexts, have showcased promising results, especially in scenarios where anomalies are subtle and span over longer durations. Additionally, considerations such as computational efficiency, ease of deployment, and real-time processing capabilities were evaluated. While CNNs and LSTMs demonstrated a balance between accuracy and computational demands, Transformer architectures, though highly accurate, require significant computational resources. In conclusion, the choice of deep learning architecture for spacecraft anomaly detection is highly contingent on the nature of the data, the type of anomalies, and operational constraints.

Juan Ciro, Daniel Galvez, Tim Schlippe et al.

This paper illustrates locality sensitive hasing (LSH) models for the identification and removal of nearly redundant data in a text dataset. To evaluate the different models, we create an artificial dataset for data deduplication using English Wikipedia articles. Area-Under-Curve (AUC) over 0.9 were observed for most models, with the best model reaching 0.96. Deduplication enables more effective model training by preventing the model from learning a distribution that differs from the real one as a result of the repeated data.