3 papers
cs.LG2026
Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies
Reza Habibi, Darian Lee, Magy Seif El-Nasr
While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training data shapes the high-level behavi…
cs.LG2026
Beyond Accuracy: Introducing a Symbolic-Mechanistic Approach to Interpretable Evaluation
Reza Habibi, Darian Lee, Magy Seif El-Nasr
Accuracy-based evaluation cannot reliably distinguish genuine generalization from shortcuts like memorization, leakage, or brittle heuristics, especially in small-data regimes. In…
cs.AI2025
What Do You Mean? Exploring How Humans and AI Interact with Symbols and Meanings in Their Interactions
Reza Habibi, Seung Wan Ha, Zhiyu Lin +5
Meaningful human-AI collaboration requires more than processing language; it demands a deeper understanding of symbols and their socially constructed meanings. While humans natural…