Interpretability

Code Defect Detection Using Pre-trained Language Models with Encoder-Decoder via Line-Level Defect Localization COLING 2024 CogBench: a large language model walks into a psychology lab ICML 2024 Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking NAACL 2024 COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits ICLR 2024 Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling NeurIPS 2024 Combinatorial Routing for Neural Trees IJCAI 2024 Common Sense Reasoning for Deep Fake Detection ECCV 2024 Compact Proofs of Model Performance via Mechanistic Interpretability NeurIPS 2024 Comparative Study of Explainability Methods for Legal Outcome Prediction EMNLP 2024 Compare without Despair: Reliable Preference Evaluation with Generation Separability EMNLP 2024 Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models NAACL 2024 Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning ACL 2024 Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods CVPR 2024 Competition-Level Problems are Effective LLM Evaluators ACL 2024 Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals ACL 2024 Compiling and Exploring a Portuguese Parliamentary Corpus: ParlaMint-PT COLING 2024 Complexity Matters: Feature Learning in the Presence of Spurious Correlations ICML 2024 Compositional Few-Shot Class-Incremental Learning ICML 2024 Compositional Preference Models for Aligning LMs ICLR 2024 Compositional Structured Explanation Generation with Dynamic Modularized Reasoning NAACL 2024 Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector ECCV 2024 Computational Argumentation: Reasoning, Dynamics, and Supporting Explainability IJCAI 2024 Computational Morphology and Lexicography Modeling of Modern Standard Arabic Nominals EACL 2024 Concept-Best-Matching: Evaluating Compositionality In Emergent Communication ACL 2024 Concept-Centric Transformers: Enhancing Model Interpretability Through Object-Centric Concept Learning Within a Shared Global Workspace WACV 2024