Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study

Online video platforms can expose young users to harmful content, but independent audits remain difficult because video annotation is costly and moderation judgments vary across languages. We audit TikTok in France, Italy, and Sweden with sockpuppet accounts representing four age personas (13, 16, 19, 40), collecting 36,971 videos from passive For-You-page scrolling and active sessions that scroll, search for harm keywords, and scroll again. To scale annotation, we validate four multimodal LLMs against native-speaker labels on a 300-video reference set. Gemini 2.5 Flash with eight sampled frames plus text performs best (aggregate kappa = 0.42), at half the per-call cost of native-video upload, and we apply it to a 10% sample for approximately \$50 in total API spend across both modalities. Keyword search returns 35-56% harmful content, a 1.5-7.5x increase over the scrolling baseline in ten of twelve country-age combinations; the spike is temporary and flattens the age differences observed in France and Sweden. Under passive scrolling, Italy has the highest harm rate at every age, with Italian age-19 reaching 48.6%. Overall, MLLM-based auditing offers a scalable approach for cross-national youth-safety audits, while provider safety filters (1.1% refusal rate) under-count the most explicit harms.

AutoSynthesis: An agentic system for automated meta-analysis

Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a research question in natural language, AutoSynthesis formulates a search strategy, retrieves scientific literature, screens candidate studies, assesses full-text eligibility, extracts quantitative statistics, computes standardized effect sizes, and finally performs random-effects meta-analysis. AutoSynthesis further supports heterogeneity analysis to examine how effect sizes vary across moderators, as well as risk-of-bias assessment. As output, AutoSynthesis produces a transparent report aligned with PRISMA guidelines. In our application, AutoSynthesis screened over 28 studies and extracted more than 20 quantitative claims. The pooled effect estimates produced by AutoSynthesis are similar to Hedges' $g$ of expert-conducted meta-analyses, indicating close agreement with manual evidence synthesis. Together, these results show that AutoSynthesis can make quantitative evidence synthesis more scalable, thereby supporting evidence-based decision-making across disciplines.

Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation

Large Language Models (LLMs) are increasingly deployed in persona-driven applications such as education, customer service, and social platforms, where models are prompted to adopt specific personas when interacting with users. While persona conditioning can improve user experience and engagement, it also raises concerns about how personality cues may interact with gender biases and stereotypes. In this work, we present a controlled study of persona-conditioned story generation in English and Hindi, where each story portrays a working professional in India producing context-specific artifacts (e.g., lesson plans, reports, letters) under systematically varied persona gender, occupational role, and personality traits from the HEXACO and Dark Triad frameworks. Across 23,400 generated stories from six state-of-the-art LLMs, we find that personality traits are significantly associated with both the magnitude and direction of gender bias. In particular, Dark Triad personality traits are consistently associated with higher gender-stereotypical representations compared to socially desirable HEXACO traits, though these associations vary across models and languages. Our findings demonstrate that gender bias in LLMs is not static but context-dependent. This suggests that persona-conditioned systems used in real-world applications may introduce uneven representational harms, reinforcing gender stereotypes in generated educational, professional, or social content.

From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics

Automated semantic annotation of broadcast television content presents distinctive challenges, combining structured audiovisual composition, domain-specific editorial patterns, and strict operational constraints. While multimodal large language models (MLLMs) have demonstrated strong general-purpose video understanding capabilities, their comparative effectiveness across pipeline architectures and input configurations in broadcast-specific settings remains empirically undercharacterized. This paper presents a systematic evaluation of multimodal annotation pipelines applied to broadcast television news in the Italian setting. We construct a domain-specific benchmark of clips labeled across four semantic dimensions: visual environment classification, topic classification, sensitive content detection, and named entity recognition. Two different pipeline architectures are evaluated across nine frontier models, including Gemini 3.0 Pro, LLaMA 4 Maverick, Qwen-VL variants, and Gemma 3, under progressively enriched input strategies combining visual signals, automatic speech recognition, speaker diarization, and metadata. Experimental results demonstrate that gains from video input are strongly model-dependent: larger models effectively leverage temporal continuity, while smaller models show performance degradation under extended multimodal context, likely due to token overload. Beyond benchmarking, the selected pipeline is deployed on 14 full broadcast episodes, with minute-level annotations integrated with normalized audience measurement data provided by an Italian media company. This integration enables correlational analysis of topic-level audience sensitivity and generational engagement divergence, demonstrating the operational viability of the proposed framework for content-based audience analytics.

Overreliance on AI in Information-seeking from Video Content

The ubiquity of multimedia content is reshaping online information spaces, particularly in social media environments. At the same time, search is being rapidly transformed by generative AI, with large language models (LLMs) routinely deployed as intermediaries between users and multimedia content to retrieve and summarize information. Despite their growing influence, the impact of LLM inaccuracies and potential vulnerabilities on multimedia information-seeking tasks remains largely unexplored. We investigate how generative AI affects accuracy, efficiency, and confidence in information retrieval from videos. We conduct an experiment with around 900 participants on 8,000+ video-based information-seeking tasks, comparing behavior across three conditions: (1) access to videos only, (2) access to videos with LLM-based AI assistance, and (3) access to videos with a deceiving AI assistant designed to provide false answers. We find that AI assistance increases accuracy by 3-7% when participants viewed the relevant video segment, and by 27-35% when they did not. Efficiency increases by 10% for short videos and 25% for longer ones. However, participants tend to over-rely on AI outputs, resulting in accuracy drops of up to 32% when interacting with the deceiving AI. Alarmingly, self-reported confidence in answers remains stable across all three conditions. Our findings expose fundamental safety risks in AI-mediated video information retrieval.

From Speech to Subtitles: Evaluating ASR Models in Subtitling Italian Television Programs

Subtitles are essential for video accessibility and audience engagement. Modern Automatic Speech Recognition (ASR) systems, built upon Encoder-Decoder neural network architectures and trained on massive amounts of data, have progressively reduced transcription errors on standard benchmark datasets. However, their performance in real-world production environments, particularly for non-English content like long-form Italian videos, remains largely unexplored. This paper presents a case study on developing a professional subtitling system for an Italian media company. To inform our system design, we evaluated four state-of-the-art ASR models (Whisper Large v2, AssemblyAI Universal, Parakeet TDT v3 0.6b, and WhisperX) on a 50-hour dataset of Italian television programs. The study highlights their strengths and limitations, benchmarking their performance against the work of professional human subtitlers. The findings indicate that, while current models cannot meet the media industry's accuracy needs for full autonomy, they can serve as highly effective tools for enhancing human productivity. We conclude that a human-in-the-loop (HITL) approach is crucial and present the production-grade, cloud-based infrastructure we designed to support this workflow.

Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Mindset in Large Language Models

In this paper, we investigate whether Large Language Models (LLMs) exhibit conspiratorial tendencies, whether they display sociodemographic biases in this domain, and how easily they can be conditioned into adopting conspiratorial perspectives. Conspiracy beliefs play a central role in the spread of misinformation and in shaping distrust toward institutions, making them a critical testbed for evaluating the social fidelity of LLMs. LLMs are increasingly used as proxies for studying human behavior, yet little is known about whether they reproduce higher-order psychological constructs such as a conspiratorial mindset. To bridge this research gap, we administer validated psychometric surveys measuring conspiracy mindset to multiple models under different prompting and conditioning strategies. Our findings reveal that LLMs show partial agreement with elements of conspiracy belief, and conditioning with socio-demographic attributes produces uneven effects, exposing latent demographic biases. Moreover, targeted prompts can easily shift model responses toward conspiratorial directions, underscoring both the susceptibility of LLMs to manipulation and the potential risks of their deployment in sensitive contexts. These results highlight the importance of critically evaluating the psychological dimensions embedded in LLMs, both to advance computational social science and to inform possible mitigation strategies against harmful uses.

Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups

Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns about their potential to reflect and amplify social biases. We investigate social identity framing in Chinese LLMs using Mandarin-specific prompts across ten representative Chinese LLMs, evaluating responses to ingroup ("We") and outgroup ("They") framings, and extending the setting to 240 social groups salient in the Chinese context. To complement controlled experiments, we further analyze Chinese-language conversations from a corpus of real interactions between users and chatbots. Across models, we observe systematic ingroup-positive and outgroup-negative tendencies, which are not confined to synthetic prompts but also appear in naturalistic dialogue, indicating that bias dynamics might strengthen in real interactions. Our study provides a language-aware evaluation framework for Chinese LLMs, demonstrating that social identity biases documented in English generalize cross-linguistically and intensify in user-facing contexts.

Evaluating AI capabilities in detecting conspiracy theories on YouTube

As a leading online platform with a vast global audience, YouTube's extensive reach also makes it susceptible to hosting harmful content, including disinformation and conspiracy theories. This study explores the use of open-weight Large Language Models (LLMs), both text-only and multimodal, for identifying conspiracy theory videos shared on YouTube. Leveraging a labeled dataset of thousands of videos, we evaluate a variety of LLMs in a zero-shot setting and compare their performance to a fine-tuned RoBERTa baseline. Results show that text-based LLMs achieve high recall but lower precision, leading to increased false positives. Multimodal models lag behind their text-only counterparts, indicating limited benefits from visual data integration. To assess real-world applicability, we evaluate the most accurate models on an unlabeled dataset, finding that RoBERTa achieves performance close to LLMs with a larger number of parameters. Our work highlights the strengths and limitations of current LLM-based approaches for online harmful content detection, emphasizing the need for more precise and robust systems.

Evaluating open-source Large Language Models for automated fact-checking

The increasing prevalence of online misinformation has heightened the demand for automated fact-checking solutions. Large Language Models (LLMs) have emerged as potential tools for assisting in this task, but their effectiveness remains uncertain. This study evaluates the fact-checking capabilities of various open-source LLMs, focusing on their ability to assess claims with different levels of contextual information. We conduct three key experiments: (1) evaluating whether LLMs can identify the semantic relationship between a claim and a fact-checking article, (2) assessing models' accuracy in verifying claims when given a related fact-checking article, and (3) testing LLMs' fact-checking abilities when leveraging data from external knowledge sources such as Google and Wikipedia. Our results indicate that LLMs perform well in identifying claim-article connections and verifying fact-checked stories but struggle with confirming factual news, where they are outperformed by traditional fine-tuned models such as RoBERTa. Additionally, the introduction of external knowledge does not significantly enhance LLMs' performance, calling for more tailored approaches. Our findings highlight both the potential and limitations of LLMs in automated fact-checking, emphasizing the need for further refinements before they can reliably replace human fact-checkers.