Interpretability

How ChatGPT is Robust for Spoken Language Understanding? Interspeech 2023 How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model NeurIPS 2023 How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks ACL 2023 How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding ICML 2023 How Many and Which Training Points Would Need to be Removed to Flip this Prediction? EACL 2023 How Much Syntactic Supervision is “Good Enough”? EACL 2023 How Well Do Large Language Models Perform on Faux Pas Tests? ACL 2023 Human-Aligned Calibration for AI-Assisted Decision Making NeurIPS 2023 Human alignment of neural network representations ICLR 2023 Human spatiotemporal pattern learning as probabilistic program synthesis NeurIPS 2023 Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings EMNLP 2023 IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding EMNLP 2023 ICICLE: Interpretable Class Incremental Continual Learning ICCV 2023 Identification of the Adversary from a Single Adversarial Example ICML 2023 Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model EMNLP 2023 Identifying Informational Sources in News Articles EMNLP 2023 Identifying Interpretable Subspaces in Image Representations ICML 2023 Identifying Statements Crucial for Awareness of Interpretive Nonsense to Prevent Communication Breakdowns EMNLP 2023 IDGI: A Framework To Eliminate Explanation Noise From Integrated Gradients CVPR 2023 IFQA: Interpretable Face Quality Assessment WACV 2023 IIEU: Rethinking Neural Feature Activation from Decision-Making ICCV 2023 Implementing Bounded Revision via Lexicographic Revision and C-revision AAAI 2023 Implications of Annotation Artifacts in Edge Probing Test Datasets CoNLL 2023 Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization CVPR 2023 Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming ACL 2023