Interpretability

Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks ICLR 2023 Test-time Augmentation for Factual Probing EMNLP 2023 Text Embeddings Reveal (Almost) As Much As Text EMNLP 2023 TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization ICLR 2023 That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context? EMNLP 2023 The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization AAAI 2023 The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks NeurIPS 2023 The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models EMNLP 2023 The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering ACL 2023 The Functional Relevance of Probed Information: A Case Study EACL 2023 The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics ACL 2023 The Internal State of an LLM Knows When It’s Lying EMNLP 2023 The Iron(ic) Melting Pot: Reviewing Human Evaluation in Humour, Irony and Sarcasm Generation EMNLP 2023 The Larger they are, the Harder they Fail: Language Models do not Recognize Identifier Swaps in Python ACL 2023 The Mechanical Bard: An Interpretable Machine Learning Approach to Shakespearean Sonnet Generation ACL 2023 Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables ICML 2023 Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests CoNLL 2023 The Parameterized Complexity of Finding Concise Local Explanations IJCAI 2023 Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection EMNLP 2023 The Solvability of Interpretability Evaluation Metrics EACL 2023 The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes NeurIPS 2023 The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks CoNLL 2023 The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding ACL 2023 Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks ICCV 2023 This Reads Like That: Deep Learning for Interpretable Natural Language Processing EMNLP 2023