Gregor Donabauer

University of Regensburg | UR · Information Science

The classification of short texts is a common subtask in Information Retrieval (IR). Recent advances in graph machine learning have led to interest in graph-based approaches for low resource scenarios, showing promise in such settings. However, existing methods face limitations such as not accounting for different meanings of the same words or cons...

This study investigates Large Language Models (LLMs) as dynamic Bayesian filters through question-asking experiments inspired by cog-nitive science. We analyse LLMs' inference errors and the evolution of uncertainty across models using repeated sampling. Building on Bertolazzi et al. (2023), we trace LLM belief states during repeated queries, findi...

The widespread use of social media has highlighted potential negative impacts on society and individuals, largely driven by recommendation algorithms that shape user behavior and social dynamics. Understanding these algorithms is essential but challenging due to the complex, distributed nature of social media networks as well as limited access to r...

The widespread use of social media has highlighted potential negative impacts on society and individuals, largely driven by recommendation algorithms that shape user behavior and social dynamics. Understanding these algorithms is essential but challenging due to the complex, distributed nature of social media networks as well as limited access to r...

LLM-based chatbots represent a significant milestone as the initial point of interaction between artificial intelligence and the general public. These chatbots offer greater flexibility compared to traditional chatbots, yet their behavior deviates notably from human interaction patterns. Current annotation schemas may not be adequately suited to ca...

Can a LLM understand dialogues, in particular from multi-party settings? In this study we explore this question through the pragmatic framework of Dialogue Acts or Speech Acts. Two tasks - classification and prediction of Dialogue Acts an - are tested with zero and few-shot learning on the STAC multi-party corpus that contains over 13000 EDUs (Ele...

Human language interactions involve complex processes beyond pure information exchange, for example, actions aimed at influencing beliefs and behaviors within a communicative context. In this paper, we propose to investigate the dialogue understanding capabilities of large language models (LLMs), particularly in multi-party settings, where challeng...

Artificial intelligence’s (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. Howe...

Social Media Artificial Intelligence algorithms provide users with engaging and personalized content. Yet, the personalization of algorithms may have a negative impact on users who lack AI literacy. The limited understanding of SM algorithms among the population suggest that adolescents are more likely to place blind trust in the information they c...

Artificial intelligence's progress holds great promise in assisting society in addressing pressing societal issues. In particular Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. T...

Educational chatbots come with a promise of interactive and personalized learning experiences, yet their development has been limited by the restricted free interaction capabilities of available platforms and the difficulty of encoding knowledge in a suitable format. Recent advances in language learning models with zero-shot learning capabilities,...

The provision of toxic content and misinformation is a frequent phenomenon in current social media with specific impact and risks for younger users. We report on efforts taken in the project Courage to mitigate and overcome these threats through dedicated educational technology inspired by psychological and pedagogical approaches. The aim is to emp...

We present a digital media literacy activity composed of (i) an educational talk and (ii) a game-based activity. The aim is to support teachers in developing learning activities to increase awareness of social media threats among students. Through this activity students directly experience phenomena like echo chambers and filter bubbles that can be...

Fake news detection has become a research area that goes way beyond a purely academic interest as it has direct implications on our society as a whole. Recent advances have primarily focused on text-based approaches. However, it has become clear that to be effective one needs to incorporate additional, contextual information such as spreading behav...

Natural language processing and other areas of artificial intelligence have seen staggering progress in recent years, yet much of this is reported with reference to somewhat limited benchmark datasets. We see the deployment of these techniques in realistic use cases as the next step in this development. In particular, much progress is still needed...

In this report, we present the project URWalking conducted at the University of Regensburg. We describe its major outcomes: Firstly, an indoor navigation system for pedestrians as a web application and as an Android app with position tracking of users in indoor and outdoor environments. Our implementation showcases that a variant of the $$A^*$$ A ∗...

Social media have become an integral part of our lives, expanding our interlinking capabilities to new levels. There is plenty to be said about their positive effects. On the other hand, however, some serious negative implications of social media have been repeatedly highlighted in recent years, pointing at various threats to society and its more v...

In a digitally led society, where social media consumption is constantly increasing, users are confronted not only with positive, but also with toxic content and dynamics like cyberbullying, racism, hate speech, or fake news [1,2,3]. Oftentimes, users are not aware of the severity (e.g., racist or homophobic comments) or level of manipulation (e...

Fake news detection has become a research area that goes way beyond a purely academic interest as it has direct implications on our society as a whole. Recent advances have primarily focused on textbased approaches. However, it has become clear that to be effective one needs to incorporate additional, contextual information such as spreading behavi...

In this paper we propose a deep learning model based on graph machine learning (i.e. Graph Attention Convolution) and a pretrained transformer language model (i.e. ELECTRA). Our model was developed to detect harmful tweets about COVID-19 and was used to tackle subtask 1C (harmful tweet detection) at the CheckThat!Lab shared task organized as part o...

Recent progress in natural language processing has been impressive in many different areas with transformer-based approaches setting new benchmarks for a wide range of applications. This development has also lowered the barriers for people outside the NLP community to tap into the tools and resources applied to a variety of domain-specific applicat...

Recent progress in natural language processing has been impressive in many different areas with transformer-based approaches setting new benchmarks for a wide range of applications. This development has also lowered the barriers for people outside the NLP community to tap into the tools and resources applied to a variety of domain-specific applicat...

This paper describes our approach (UR-mSBD) to address the shared task on Sentence End and Punctuation Prediction in NLG Text (SEPP-NLG) organised as part of SwissText 2021. We participated in Subtask 1 (fully un-punctuated sentences-full stop detection) and submitted a run for every featured language (English, German, French, Italian). Our submiss...

We identify automated landmark salience assessment in indoor environments as a problem related to pedestrian navigation systems that has not yet received much attention but is nevertheless of practical relevance. We therefore evaluate an approach based on visual information using images to capture the landmarks’ outward appearance. In this context...

The rise of deep learning methods has transformed the research area of natural language processing beyond recognition. New benchmark performances are reported on a daily basis ranging from machine translation to questionanswering. Yet, some of the unsolved practical research questions are not in the spotlight and this includes, for example, issues...