Eric Wong

NSF-SciFy: Mining the NSF Awards Database for Scientific Claims ACL 2026 Adaptively profiling models with task elicitation EMNLP 2025 Avoiding Copyright Infringement via Large Language Model Unlearning NAACL 2025 Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing IJCNLP 2025 DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning ICML 2025 Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs EMNLP 2025 Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference ICLR 2025 NSF-SciFy: Mining the NSF Awards Database for Scientific Claims EMNLP 2025 Probabilistic Soundness Guarantees in LLM Reasoning Chains EMNLP 2025 Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups ICML 2025 Towards Style Alignment in Cross-Cultural Translation ACL 2025 AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties NeurIPS 2024 Data-Efficient Learning with Neural Programs NeurIPS 2024 DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation ICML 2024 Initialization Matters for Adversarial Transfer Learning CVPR 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NeurIPS 2024 SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation ICLR 2024 Towards Compositionality in Concept Learning ICML 2024 A Data-Based Perspective on Transfer Learning CVPR 2023 Adversarial Robustness in Discontinuous Spaces via Alternating Sampling & Descent WACV 2023 Comparing Styles across Languages EMNLP 2023 Do Machine Learning Models Learn Statistical Rules Inferred from Data? ICML 2023 Faithful Chain-of-Thought Reasoning IJCNLP 2023 Stability Guarantees for Feature Attributions with Multiplicative Smoothing NeurIPS 2023 Certified Patch Robustness via Smoothed Vision Transformers CVPR 2022 Missingness Bias in Model Debugging ICLR 2022 Learning perturbation sets for robust machine learning ICLR 2021 Leveraging Sparse Linear Layers for Debuggable Deep Networks ICML 2021 Adversarial Robustness Against the Union of Multiple Perturbation Models ICML 2020 Fast is better than free: Revisiting adversarial training ICLR 2020 Overfitting in adversarially robust deep learning ICML 2020 Wasserstein Adversarial Examples via Projected Sinkhorn Iterations ICML 2019 Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope ICML 2018 Scaling provable adversarial defenses NeurIPS 2018 A Semismooth Newton Method for Fast, Generic Convex Programming ICML 2017