Tag
Forecast-Dojo is a replayable environment for benchmarking and training LLM forecasting agents, combining resolved prediction-market questions with dated news to enable repeated evaluation and learning from outcomes.
The article investigates how Flock became widely criticized or targeted, likely in the technology sector.
The article discusses concerns about AI being used to create bioweapons but argues that the risk is low due to practical bottlenecks and human oversight, citing experts like David Bellamy and Jason Kelly.
This paper presents an LLM-based pipeline for analyzing media bias and framing in online news, tested on Albanian articles with moderate agreement in annotations compared to automated methods.
This paper analyzes 28,592 French news headlines about La France insoumise and Rassemblement National using an LLM annotation pipeline, finding asymmetric role framing where LFI is more often framed as aggressors and RN as strategic actors.
This paper compares top-down and bottom-up approaches for collecting text-based data about disasters from news articles, using German news about landslides as a case study.