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 challenges like speaker identification and turn-taking are common. Through experiments on the game-based STAC dataset, we explore zero and few-shot learning approaches for dialogue act classification in a multi-party game setting. Our intuition is that LLMs may excel in tasks framed through examples rather than formal descriptions, influenced by a range of pragmatic features like information presentation order in prompts and others. We also explore the models’ predictive abilities regarding future dialogue acts and study integrating information on dialogue act sequences to improve predictions. Our findings suggest that ChatGPT can keep up with baseline models trained from scratch for classification of certain dialogue act types but also reveal biases and limitations associated with the approach. These insights can be valuable for the development of multi-party chatbots and we try to point out directions for future research towards nuanced understanding and adaptation in diverse conversational contexts

Pre-training of neural networks has recently revolutionized the field of Natural Language Processing (NLP) and has before demonstrated its effectiveness in computer vision. At the same time, advances around the detection of fake news were mainly driven by the context-based paradigm, where different types of signals (e.g. from social media) form graph-like structures that hold contextual information apart from the news article to classify. We propose to merge these two developments by applying pre-training of Graph Neural Networks (GNNs) in the domain of context-based fake news detection. Our experiments provide an evaluation of different pre-training strategies for graph-based misinformation detection and demonstrate that transfer learning does currently not lead to significant improvements over training a model from scratch in the domain. We argue that a major current issue is the lack of suitable large-scale resources that can be used for pre-training.

Social media have become an integral part of our daily lives, yet they have also resulted in various negative effects on users, ranging from offensive or hateful content to the spread of misinformation. In recent years, numerous automated approaches have been proposed to identify and combat such harmful content. However, it is crucial to recognize the human aspect of users who engage with this content in designing efforts to mitigate these threats. We propose to incorporate principles of behavioral science, specifically the concept of nudging into social media platforms. Our approach involves augmenting social media feeds with informative diagrams, which provide insights into the content that users are presented. The goal of our work is to empower social media users to make well-informed decisions for themselves and for others within these platforms. Nudges serve as a means to gently draw users’ attention to content in an unintrusive manner, a crucial consideration in the context of social media. To evaluate the effectiveness of our approach, we conducted a user study involving 120 Italian-speaking participants who interacted with a social media interface augmented with these nudging diagrams. Participants who had used the augmented interface were able to outperform those using the plain interface in a successive harmful content detection test where nudging diagrams were not visible anymore. Our findings demonstrate that our approach significantly improves users’ awareness of potentially harmful content with effects lasting beyond the duration of the interaction. In this work, we provide a comprehensive overview of our experimental materials and setup, present our findings, and refer to the limitations identified during our study.

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 applications. The bottleneck however still remains the lack of annotated gold-standard collections as soon as one’s research or professional interest falls outside the scope of what is readily available. One such area is genocide-related research (also including the work of experts who have a professional interest in accessing, exploring and searching large-scale document collections on the topic, such as lawyers). We present GTC (Genocide Transcript Corpus), the first annotated corpus of genocide-related court transcripts which serves three purposes: (1) to provide a first reference corpus for the community, (2) to establish benchmark performances (using state-of-the-art transformer-based approaches) for the new classification task of paragraph identification of violence-related witness statements, (3) to explore first steps towards transfer learning within the domain. We consider our contribution to be addressing in particular this year’s hot topic on Language Technology for All.