17 papers
Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
Shichang Zhang, Hongzhe Du, Jiaqi W. Ma +1
Modern AI systems are typically developed through multiple stages-pretraining, fine-tuning rounds, and subsequent adaptation or alignment, where each stage builds on the previous o…
A Unified Theory of Random Projection for Influence Functions
Pingbang Hu, Yuzheng Hu, Jiaqi W. Ma +1
Influence functions and related data attribution scores take the form of , where is a curvature operator. In modern overparametrized models,…
FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
Xingjian Zhang, Sophia Moylan, Ziyang Xiong +3
Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human researchers and emerging AI systems.…
Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks
Xinhe Wang, Jin Huang, Xingjian Zhang +2
Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probe…
A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
Yiwen Tu, Pingbang Hu, Jiaqi Ma
Machine unlearning updates machine learning models to remove information from specific training samples, complying with data protection regulations that allow individuals to reques…
GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection
Pingbang Hu, Joseph Melkonian, Weijing Tang +2
Gradient-based data attribution methods, such as influence functions, are critical for understanding the impact of individual training samples without requiring repeated model retr…