A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Keyon Vafa, Peter G. Chang, Ashesh Rambachan, et al.
Proposes an inductive bias probe to evaluate whether foundation models capture deeper domain structure, finding they often fail to generalize beyond training tasks.
Roberto Navigli, Simone Conia, Björn Roß
This paper surveys bias in LLMs from data selection to social biases like gender, ethnicity, and religion, and outlines measurement and mitigation directions.
Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, et al.
A comprehensive survey of bias evaluation and mitigation techniques for LLMs, proposing taxonomies for metrics, datasets, and mitigation methods.
Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson
Proposes two learning strategies to train neural models that are more robust to dataset biases and transfer better to out-of-domain datasets.
Unknown
LAMBERT enhances RoBERTa with layout embeddings and relative bias for layout-aware document understanding without raw images.
Jacob T. Shreve, Sadia A. Khanani, Tufia C. Haddad
Reviews AI applications in oncology, including FDA-approved computer vision, multi-cancer detection, and ethical challenges like bias and interpretability.
Ze Liu, Han Hu, Yutong Lin, et al.
Swin Transformer V2 introduces post-norm, cosine attention, log-spaced position bias, and self-supervised pretraining to scale vision transformers to 3B parameters.
André Bauer, Simon Trapp, Michael Stenger, et al.
A comprehensive survey of synthetic data generation methods, their advantages, and applications when real data is scarce, costly, or biased.
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, et al.
This paper examines the dual nature of foundation models, highlighting their transformative potential alongside significant risks such as bias, misuse, and environmental impact.
W. Holmes, Kaśka Porayska‐Pomsta, Ken Holstein, et al.
This paper surveys 60 AIED researchers to identify ethical gaps and proposes a multidisciplinary framework for fairness, accountability, transparency, bias, autonomy, agency, and inclusion in AI education.
Unknown
Spectral neural operators avoid aliasing bias in integral transform-based neural operators.