3 papers
cs.SE2026
Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis
Jacqueline L. Mitchell, Chao Wang
Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API co…
cs.CL2026
Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing
Jinchang Zhu, Jindong Li, Chengyu Zou +4
Long-context adaptation is often viewed as window scaling, but this misses a token-level supervision mismatch: in packed training with document masking, each target token's effecti…
cs.LG2026
Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation
Brian Hyeongseok Kim, Jacqueline L. Mitchell, Chao Wang
Interpreting the inference-time behavior of deep neural networks remains a challenging problem. Existing approaches to counterfactual explanation typically ask: What is the closest…