Ljubisa Bojic

Bojana Bodroza, Bojana M. Dinic, Ljubisa Bojic

As Large Language Models (LLMs) continue to gain popularity due to their human-like traits and the intimacy they offer to users, their societal impact inevitably expands. This leads to the rising necessity for comprehensive studies to fully understand LLMs and reveal their potential opportunities, drawbacks, and overall societal impact. With that in mind, this research conducted an extensive investigation into seven LLM's, aiming to assess the temporal stability and inter-rater agreement on their responses on personality instruments in two time points. In addition, LLMs personality profile was analyzed and compared to human normative data. The findings revealed varying levels of inter-rater agreement in the LLMs responses over a short time, with some LLMs showing higher agreement (e.g., LIama3 and GPT-4o) compared to others (e.g., GPT-4 and Gemini). Furthermore, agreement depended on used instruments as well as on domain or trait. This implies the variable robustness in LLMs' ability to reliably simulate stable personality characteristics. In the case of scales which showed at least fair agreement, LLMs displayed mostly a socially desirable profile in both agentic and communal domains, as well as a prosocial personality profile reflected in higher agreeableness and conscientiousness and lower Machiavellianism. Exhibiting temporal stability and coherent responses on personality traits is crucial for AI systems due to their societal impact and AI safety concerns.

Ljubisa Bojic, Alexander Felfernig, Bojana Dinic et al.

Social media platforms mediate how billions form opinions and engage with public discourse. As autonomous AI agents increasingly participate in these spaces, understanding their behavioral fidelity becomes critical for platform governance and democratic resilience. Previous work demonstrates that LLM-powered agents can replicate aggregate survey responses, yet few studies test whether agents can predict specific individuals' reactions to specific content. This study benchmarks LLM-based agents' accuracy in predicting human social media reactions (like, dislike, comment, share, no reaction) across 120,000+ unique agent-persona combinations derived from 1,511 Serbian participants and 27 large language models. In Study 1, agents achieved 70.7% overall accuracy, with LLM choice producing a 13 percentage-point performance spread. Study 2 employed binary forced-choice (like/dislike) evaluation with chance-corrected metrics. Agents achieved Matthews Correlation Coefficient (MCC) of 0.29, indicating genuine predictive signal beyond chance. However, conventional text-based supervised classifiers using TF-IDF representations outperformed LLM agents (MCC of 0.36), suggesting predictive gains reflect semantic access rather than uniquely agentic reasoning. The genuine predictive validity of zero-shot persona-prompted agents warns against potential manipulation through easily deploying swarms of behaviorally distinct AI agents on social media, while simultaneously offering opportunities to use such agents in simulations for predicting polarization dynamics and informing AI policy. The advantage of using zero-shot agents is that they require no task-specific training, making their large-scale deployment easy across diverse contexts. Limitations include single-country sampling. Future research should explore multilingual testing and fine-tuning approaches.

Ljubisa Bojic, Predrag Kovacevic, Milan Cabarkapa

As Large Language Models (LLMs) become increasingly integrated into everyday life as general purpose multimodal AI systems, their capabilities to simulate human understanding are under examination. This study investigates LLMs ability to interpret linguistic pragmatics, which involves context and implied meanings. Using Grice communication principles, we evaluated both LLMs (GPT-2, GPT-3, GPT-3.5, GPT-4, and Bard) and human subjects (N = 147) on dialogue-based tasks. Human participants included 71 primarily Serbian students and 76 native English speakers from the United States. Findings revealed that LLMs, particularly GPT-4, outperformed humans. GPT4 achieved the highest score of 4.80, surpassing the best human score of 4.55. Other LLMs performed well: GPT 3.5 scored 4.10, Bard 3.75, and GPT-3 3.25. GPT-2 had the lowest score of 1.05. The average LLM score was 3.39, exceeding the human cohorts averages of 2.80 (Serbian students) and 2.34 (U.S. participants). In the ranking of all 155 subjects (including LLMs and humans), GPT-4 secured the top position, while the best human ranked second. These results highlight significant progress in LLMs ability to simulate understanding of linguistic pragmatics. Future studies should confirm these findings with more dialogue-based tasks and diverse participants. This research has important implications for advancing general-purpose AI models in various communication-centered tasks, including potential application in humanoid robots in the future.

Ljubisa Bojic, Matteo Cinelli, Dubravko Culibrk et al.

This paper explores the potential of a multidisciplinary approach to testing and aligning artificial intelligence (AI), specifically focusing on large language models (LLMs). Due to the rapid development and wide application of LLMs, challenges such as ethical alignment, controllability, and predictability of these models emerged as global risks. This study investigates an innovative simulation-based multi-agent system within a virtual reality framework that replicates the real-world environment. The framework is populated by automated 'digital citizens,' simulating complex social structures and interactions to examine and optimize AI. Application of various theories from the fields of sociology, social psychology, computer science, physics, biology, and economics demonstrates the possibility of a more human-aligned and socially responsible AI. The purpose of such a digital environment is to provide a dynamic platform where advanced AI agents can interact and make independent decisions, thereby mimicking realistic scenarios. The actors in this digital city, operated by the LLMs, serve as the primary agents, exhibiting high degrees of autonomy. While this approach shows immense potential, there are notable challenges and limitations, most significantly the unpredictable nature of real-world social dynamics. This research endeavors to contribute to the development and refinement of AI, emphasizing the integration of social, ethical, and theoretical dimensions for future research.

Ljubisa Bojic, Zorica Dodevska, Yashar Deldjoo et al.

Given the exponential advancement in AI technologies and the potential escalation of harmful effects from recommendation systems, it is crucial to simulate and evaluate these effects early on. Doing so can help prevent possible damage to both societies and technology companies. This paper introduces the Recommender Systems LLMs Playground (RecSysLLMsP), a novel simulation framework leveraging Large Language Models (LLMs) to explore the impacts of different content recommendation setups on user engagement and polarization in social networks. By creating diverse AI agents (AgentPrompts) with descriptive, static, and dynamic attributes, we assess their autonomous behaviour across three scenarios: Plurality, Balanced, and Similarity. Our findings reveal that the Similarity Scenario, which aligns content with user preferences, maximizes engagement while potentially fostering echo chambers. Conversely, the Plurality Scenario promotes diverse interactions but produces mixed engagement results. Our study emphasizes the need for a careful balance in recommender system designs to enhance user satisfaction while mitigating societal polarization. It underscores the unique value and challenges of incorporating LLMs into simulation environments. The benefits of RecSysLLMsP lie in its potential to calculate polarization effects, which is crucial for assessing societal impacts and determining user engagement levels with diverse recommender system setups. This advantage is essential for developing and maintaining a successful business model for social media companies. However, the study's limitations revolve around accurately emulating reality. Future efforts should validate the similarity in behaviour between real humans and AgentPrompts and establish metrics for measuring polarization scores.

Ljubisa Bojic, Joerg Matthes, Agariadne Dwinggo Samala et al.

The emergence of the metaverse - envisioned as a hyperreal virtual universe enabling boundless human interaction - has the potential to revolutionize our conception of media. This transformation could alter society as we know it. This paper identifies addictive features of social media, including immersion, interactivity, real-time access, and personalization. These features are examined within the context of virtual reality through a literature review and content analysis, aimed at exploring the potential consequences of metaverse development. From an initial pool of 193,218 documents, a refined selection of N = 44 relevant papers formed the basis of our qualitative analysis. About half of the analyzed papers indicate that these features contribute to VR addiction. Interestingly, the same features that contribute to addictive behaviors can also be harnessed for positive therapeutic interventions of VR, particularly in treating addictions and managing mental health conditions. This duality, observed in the other half of the papers, emphasizes the complex role of VR technologies, suggesting that they can serve as a substitute for other addictions. This phenomenon is placed into the historical context of evolving media technologies that increasingly mimic reality. The complex interplay of factors contributing to addiction necessitates the development of algorithmic solutions that actively curate diverse offerings, rather than promoting a closed loop of like-minded views. Traditional models of addiction should be adapted to address these unique challenges. Finally, the discussion turned to the implications of these findings for a society where the metaverse is widely accepted as a mainstream technology.

Ljubisa Bojic, Olga Zagovora, Asta Zelenkauskaite et al.

In the era of rapid digital communication, vast amounts of textual data are generated daily, demanding efficient methods for latent content analysis to extract meaningful insights. Large Language Models (LLMs) offer potential for automating this process, yet comprehensive assessments comparing their performance to human annotators across multiple dimensions are lacking. This study evaluates the reliability, consistency, and quality of seven state-of-the-art LLMs, including variants of OpenAI's GPT-4, Gemini, Llama, and Mixtral, relative to human annotators in analyzing sentiment, political leaning, emotional intensity, and sarcasm detection. A total of 33 human annotators and eight LLM variants assessed 100 curated textual items, generating 3,300 human and 19,200 LLM annotations, with LLMs evaluated across three time points to examine temporal consistency. Inter-rater reliability was measured using Krippendorff's alpha, and intra-class correlation coefficients assessed consistency over time. The results reveal that both humans and LLMs exhibit high reliability in sentiment analysis and political leaning assessments, with LLMs demonstrating higher internal consistency than humans. In emotional intensity, LLMs displayed higher agreement compared to humans, though humans rated emotional intensity significantly higher. Both groups struggled with sarcasm detection, evidenced by low agreement. LLMs showed excellent temporal consistency across all dimensions, indicating stable performance over time. This research concludes that LLMs, especially GPT-4, can effectively replicate human analysis in sentiment and political leaning, although human expertise remains essential for emotional intensity interpretation. The findings demonstrate the potential of LLMs for consistent and high-quality performance in certain areas of latent content analysis.

Ljubisa Bojic, Nikola Prodanovic, Agariadne Dwinggo Samala

The rapid growth of online news platforms has led to an increased need for reliable methods to evaluate the quality and credibility of news articles. This paper proposes a comprehensive framework to analyze online news texts using natural language processing (NLP) techniques, particularly a language model specifically trained for this purpose, alongside other well-established NLP methods. The framework incorporates ten journalism standards-objectivity, balance and fairness, readability and clarity, sensationalism and clickbait, ethical considerations, public interest and value, source credibility, relevance and timeliness, factual accuracy, and attribution and transparency-to assess the quality of news articles. By establishing these standards, researchers, media organizations, and readers can better evaluate and understand the content they consume and produce. The proposed method has some limitations, such as potential difficulty in detecting subtle biases and the need for continuous updating of the language model to keep pace with evolving language patterns.

Ljubisa Bojic, Dylan Seychell, Milan Cabarkapa

As general-purpose artificial intelligence systems become increasingly integrated into society and are used for information seeking, content generation, problem solving, textual analysis, coding, and running processes, it is crucial to assess their long-term impact on humans. This research explores the sentiment of large language models (LLMs) and humans toward artificial general intelligence (AGI) using a Likert-scale survey. Seven LLMs, including GPT-4 and Bard, were analyzed and compared with sentiment data from three independent human sample populations. Temporal variations in sentiment were also evaluated over three consecutive days. The results show a diversity in sentiment scores among LLMs, ranging from 3.32 to 4.12 out of 5. GPT-4 recorded the most positive sentiment toward AGI, while Bard leaned toward a neutral sentiment. In contrast, the human samples showed a lower average sentiment of 2.97. The analysis outlines potential conflicts of interest and biases in the sentiment formation of LLMs, and indicates that LLMs could subtly influence societal perceptions. To address the need for regulatory oversight and culturally grounded assessments of AI systems, we introduce the Societal AI Alignment and Sentiment Benchmark (SAAS-AI), which leverages multidimensional prompts and empirically validated societal value frameworks to evaluate language model outputs across temporal, model, and multilingual axes. This benchmark is designed to guide policymakers and AI agencies, including within frameworks such as the EU AI Act, by providing robust, actionable insights into AI alignment with human values, public sentiment, and ethical norms at both national and international levels. Future research should further refine the operationalization of the SAAS-AI benchmark and systematically evaluate its effectiveness through comprehensive empirical testing.