Interpretability

Manifold-Aligned Counterfactual Explanations for Neural Networks AISTATS 2024 Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution ICML 2024 ManiFPT: Defining and Analyzing Fingerprints of Generative Models CVPR 2024 Mapping the Multiverse of Latent Representations ICML 2024 MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction EMNLP 2024 MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning NeurIPS 2024 MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection NAACL 2024 MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective ICML 2024 Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks ICLR 2024 MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts ICLR 2024 MAVEN-FACT: A Large-scale Event Factuality Detection Dataset EMNLP 2024 MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes CVPR 2024 MD tree: a model-diagnostic tree grown on loss landscape ICML 2024 Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models NAACL 2024 Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models ACL 2024 Measuring Per-Unit Interpretability at Scale Without Humans NeurIPS 2024 Measuring Political Bias in Large Language Models: What Is Said and How It Is Said ACL 2024 Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NeurIPS 2024 Measuring Stochastic Data Complexity with Boltzmann Influence Functions ICML 2024 Measuring the Groundedness of Legal Question-Answering Systems EMNLP 2024 Measuring the Inconsistency of Large Language Models in Preferential Ranking ACL 2024 Mechanistic? EMNLP 2024 Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks ICLR 2024 Mechanistic Neural Networks for Scientific Machine Learning ICML 2024 Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations EMNLP 2024