Interpretability

AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction ICLR 2024 Aligning Language Models to Explicitly Handle Ambiguity EMNLP 2024 Aligning Large and Small Language Models via Chain-of-Thought Reasoning EACL 2024 A Little of That Human Touch: Achieving Human-Centric Explainable AI via Argumentation IJCAI 2024 All Models are Wrong, But Some are Deadly: Inconsistencies in Emotion Detection in Suicide-related Tweets EMNLP 2024 Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction NeurIPS 2024 AlphaIntellect at SemEval-2024 Task 6: Detection of Hallucinations in Generated Text SemEval 2024 Ambiguity-Aware Abductive Learning ICML 2024 A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task ACL 2024 A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity ICML 2024 AMREx: AMR for Explainable Fact Verification EMNLP 2024 A Multimodal Automated Interpretability Agent ICML 2024 A Multi-Perspective Analysis of Memorization in Large Language Models EMNLP 2024 An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L EMNLP 2024 Analysing the Generalisation and Reliability of Steering Vectors NeurIPS 2024 Analysing Translation Artifacts: A Comparative Study of LLMs, NMTs, and Human Translations EMNLP 2024 Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts ICML 2024 Analysis of Pathological Speech – Pitfalls along the Way Interspeech 2024 Analyzing Chain-of-thought Prompting in Black-Box Large Language Models via Estimated V-information COLING 2024 Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions AISTATS 2024 Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps ICLR 2024 Analyzing Interpretability of Summarization Model with Eye-gaze Information COLING 2024 Analyzing Semantic Change through Lexical Replacements ACL 2024 Analyzing the Use of Metaphors in News Editorials for Political Framing NAACL 2024 An Audit on the Perspectives and Challenges of Hallucinations in NLP EMNLP 2024