Interpretability

Too Big to Fail: Larger Language Models are Disproportionately Resilient to Induction of Dementia-Related Linguistic Anomalies ACL 2024 ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models EMNLP 2024 TopicGPT: A Prompt-based Topic Modeling Framework NAACL 2024 Topological Analysis for Detecting Anomalies in dependent sequences: application to Time Series JMLR 2024 Total Variation Floodgate for Variable Importance Inference in Classification ICML 2024 To Tell The Truth: Language of Deception and Language Models NAACL 2024 Towards a Complete Benchmark on Video Moment Localization AISTATS 2024 Towards a Perceptual Evaluation Framework for Lighting Estimation CVPR 2024 Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics NeurIPS 2024 Towards Automatic Boundary Detection for Human-AI Collaborative Hybrid Essay in Education AAAI 2024 Towards Benchmarking Situational Awareness of Large Language Models:Comprehensive Benchmark, Evaluation and Analysis EMNLP 2024 Towards Best Practices of Activation Patching in Language Models: Metrics and Methods ICLR 2024 Towards Compositionality in Concept Learning ICML 2024 Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset COLING 2024 Towards Explainability in Legal Outcome Prediction Models NAACL 2024 Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method EMNLP 2024 Towards Explainable Computerized Adaptive Testing with Large Language Model EMNLP 2024 Towards Explainable Multi-Label Text Classification: A Multi-Task Rationalisation Framework for Identifying Indicators of Forced Labour EMNLP 2024 Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery ICLR 2024 Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark ICLR 2024 Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph ICML 2024 Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation COLING 2024 Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach AISTATS 2024 Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation ICML 2024 Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales NAACL 2024