Many commercial and open-source models claim to detect machine-generated text with extremely high accuracy (99% or more). However, very few of these detectors are evaluated on shared benchmark datasets and even when they are, the datasets used for evaluation are insufficiently challenging—lacking variations in sampling strategy, adversarial attacks, and open-source generative models. In this work we present RAID: the largest and most challenging benchmark dataset for machine-generated text detection. RAID includes over 6 million generations spanning 11 models, 8 domains, 11 adversarial attacks and 4 decoding strategies. Using RAID, we evaluate the out-of-domain and adversarial robustness of 8 open- and 4 closed-source detectors and find that current detectors are easily fooled by adversarial attacks, variations in sampling strategies, repetition penalties, and unseen generative models. We release our data along with a leaderboard to encourage future research.

Large language models (LLMs) are increasingly being utilised across a range of tasks and domains, with a burgeoning interest in their application within the field of journalism. This trend raises concerns due to our limited understanding of LLM behaviour in this domain, especially with respect to political bias. Existing studies predominantly focus on LLMs undertaking political questionnaires, which offers only limited insights into their biases and operational nuances. To address this gap, our study establishes a new curated dataset that contains 2,100 human-written articles and utilises their descriptions to generate 56,700 synthetic articles using nine LLMs. This enables us to analyse shifts in properties between human-authored and machine-generated articles, with this study focusing on political bias, detecting it using both supervised models and LLMs. Our findings reveal significant disparities between base and instruction-tuned LLMs, with instruction-tuned models exhibiting consistent political bias. Furthermore, we are able to study how LLMs behave as classifiers, observing their display of political bias even in this role. Overall, for the first time within the journalistic domain, this study outlines a framework and provides a structured dataset for quantifiable experiments, serving as a foundation for further research into LLM political bias and its implications.

We present the Verifee dataset: a multimodal dataset of news articles with fine-grained trustworthiness annotations. We bring a diverse set of researchers from social, media, and computer sciences aboard to study this interdisciplinary problem holistically and develop a detailed methodology that assesses the texts through the lens of editorial transparency, journalist conventions, and objective reporting while penalizing manipulative techniques. We collect over 10,000 annotated articles from 60 Czech online news sources. Each item is categorized into one of the 4 proposed classes on the credibility spectrum – ranging from entirely trustworthy articles to deceptive ones – and annotated of its manipulative attributes. We fine-tune prominent sequence-to-sequence language models for the trustworthiness classification task on our dataset and report the best F-1 score of 0.53. We open-source the dataset, annotation methodology, and annotators’ instructions in full length at https://www.verifee.ai/research/ to enable easy build-up work.