Interpretability

Prompts have evil twins EMNLP 2024 Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks ACL 2024 Properties and Challenges of LLM-Generated Explanations NAACL 2024 PropTest: Automatic Property Testing for Improved Visual Programming EMNLP 2024 Prospector Heads: Generalized Feature Attribution for Large Models & Data ICML 2024 ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data ICML 2024 ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition IJCAI 2024 Prototype Learning for Explainable Brain Age Prediction WACV 2024 Prototypical Transformer As Unified Motion Learners ICML 2024 ProTransformer: Robustify Transformers via Plug-and-Play Paradigm NeurIPS 2024 Provably Better Explanations with Optimized Aggregation of Feature Attributions ICML 2024 Provably Robust Conformal Prediction with Improved Efficiency ICLR 2024 Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output EMNLP 2024 Pruning neural network models for gene regulatory dynamics using data and domain knowledge NeurIPS 2024 PSentScore: Evaluating Sentiment Polarity in Dialogue Summarization COLING 2024 PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety ACL 2024 PUZZLES: A Benchmark for Neural Algorithmic Reasoning NeurIPS 2024 pyvene: A Library for Understanding and Improving PyTorch Models via Interventions NAACL 2024 PyXAI: An XAI Library for Tree-Based Models IJCAI 2024 QORA: Zero-Shot Transfer via Interpretable Object-Relational Model Learning ICML 2024 Q-SENN: Quantized Self-Explaining Neural Networks AAAI 2024 QualEval: Qualitative Evaluation for Model Improvement NAACL 2024 Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing NeurIPS 2024 Quantifying and Enhancing Multi-modal Robustness with Modality Preference ICLR 2024 Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective EMNLP 2024