KAUST ·
This is a brief statement indicating that the content is from King Abdullah University of Science and Technology (KAUST). It mentions KAUST Discovery and notes the late King Abdullah bin Abdulaziz Al Saud. It also states that all rights are reserved. Why it matters: This is a standard copyright and attribution notice for KAUST content.
MBZUAI ·
Xiuying Chen from KAUST presented her work on improving the trustworthiness of AI-generated text, focusing on accuracy and robustness. Her research analyzes causes of hallucination in language models related to semantic understanding and neglect of input knowledge, and proposes solutions. She also demonstrated vulnerabilities of language models to noise and enhances robustness using augmentation techniques. Why it matters: Improving the reliability of AI-generated text is crucial for its deployment in sensitive domains like healthcare and scientific discovery, where accuracy is paramount.
arXiv ·
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.
MBZUAI ·
MBZUAI Professor Kun Zhang received a Test of Time Award Honorable Mention at ICML 2022 for his 2012 paper “On causal and anticausal learning." The paper, co-authored with researchers from the Max-Planck Institute, is considered foundational for causal learning in machine learning. Zhang's work demonstrated the importance of causality for machine learning tasks, helping to shift views in the field. Why it matters: This award highlights the growing recognition of causal AI research and MBZUAI's role in advancing the field.
MBZUAI ·
Researchers from MBZUAI developed "uncertainty quantification heads" (UQ heads) to detect hallucinations in language models by probing internal states and estimating the credibility of generated text. UQ heads leverage attention maps and logits to identify potential hallucinations without altering the model's generation process or relying on external knowledge. The team found that UQ heads achieved state-of-the-art performance in claim-level hallucination detection across different domains and languages. Why it matters: This approach offers a more efficient and accurate method for identifying hallucinations, improving the reliability and trustworthiness of language models in various applications.
arXiv ·
Researchers from MBZUAI have introduced VideoMolmo, a large multimodal model for spatio-temporal pointing conditioned on textual descriptions. The model incorporates a temporal module with an attention mechanism and a temporal mask fusion pipeline using SAM2 for improved coherence across video sequences. They also curated a dataset of 72k video-caption pairs and introduced VPoS-Bench, a benchmark for evaluating generalization across real-world scenarios, with code and models publicly available.