MBZUAI student Zain Muhammad Mujahid is researching methods to detect media bias using NLP and LLMs. His approach profiles bias across media outlets using LLMs like ChatGPT to predict bias based on 16 identifiers. The research aims to develop a tool that instantly provides a bias profile for a given media URL. Why it matters: This research has the potential to combat misinformation and enhance media literacy in the region by providing tools to identify biased reporting, and it is expanding to Arabic and other languages.
A new methodology emulating fact-checker criteria assesses news outlet factuality and bias using LLMs. The approach uses prompts based on fact-checking criteria to elicit and aggregate LLM responses for predictions. Experiments demonstrate improvements over baselines, with error analysis on media popularity and region, and a released dataset/code at https://github.com/mbzuai-nlp/llm-media-profiling.
Researchers from MBZUAI, University of Washington, and other institutions presented studies at EMNLP 2024 exploring how LLMs represent cultures. A survey analyzed dozens of recent studies on LLMs and culture and proposes a new framework for future research. The survey found that there is no widely accepted definition of 'culture' in NLP, making it challenging to interpret how models represent culture through language. Why it matters: This highlights a key gap in the field and emphasizes the need for a more rigorous and consistent understanding of culture in AI, especially as LLMs become more globally integrated.
Muhammad Arslan Manzoor became MBZUAI's first NLP Ph.D. graduate, focusing his research on media bias under Professor Preslav Nakov. His thesis, 'MGM,' explored using audience overlap graphs to predict the factuality and bias of news media, an approach that differs from traditional textual analysis. Manzoor's work aims to improve the efficiency of media profiling in real-time by leveraging relationships captured in media graphs. Why it matters: This research offers innovative methods for identifying bias in news, which is crucial for promoting informed social discourse and combating disinformation in the region.
This study introduces a Probabilistic Graphical Model (PGM) framework utilizing Pearl's do-operator to causally audit LLM safety mechanisms, specifically isolating the effect of injecting cultural demographics into prompts. A large-scale empirical analysis was conducted across seven instruction-tuned models from diverse origins, including the UAE's Falcon3-7B, as well as models from the US, Europe, China, and India, using ToxiGen and BOLD datasets. The findings revealed a disparity between observational and interventional bias, demonstrating that standard fairness metrics can overestimate demographic bias. Western models exhibited higher causal refusal rates for specific demographic groups, while Eastern models showed low overall intervention rates with targeted sensitivities toward regional demographics. Why it matters: This research highlights the geopolitical nuances of LLM safety alignment and the potential for demographic-sensitive over-triggering to restrict benign discourse, which is particularly relevant for diverse regions like the Middle East in developing culturally-aware AI.
MBZUAI researchers introduce FAID, a fine-grained AI-generated text detection framework capable of classifying text as human-written, LLM-generated, or collaboratively written. FAID utilizes multi-level contrastive learning and multi-task auxiliary classification to capture authorship and model-specific characteristics, and can identify the underlying LLM family. The framework outperforms existing baselines, especially in generalizing to unseen domains and new LLMs, and includes a multilingual, multi-domain dataset called FAIDSet.
A study by MBZUAI's Preslav Nakov and Cornell co-authors examines how to develop systems that detect fake news in a landscape where text is generated by humans and machines. The research, presented at the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, analyzes fake news detectors' ability to identify human- and machine-written content. The study highlights biases in current detectors, which tend to classify machine-written news as fake and human-written news as true. Why it matters: Addressing these biases is crucial as machine-generated content becomes more prevalent in both real and fake news, requiring more nuanced detection methods.