Interpretability

The Craft of Selective Prediction: Towards Reliable Case Outcome Classification - An Empirical Study on European Court of Human Rights Cases EMNLP 2024 The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models ICLR 2024 The Effective Number of Shared Dimensions Between Paired Datasets AISTATS 2024 The Effect of Surprisal on Reading Times in Information Seeking and Repeated Reading CoNLL 2024 The Elephant in the Room: Ten Challenges of Computational Detection of Rhetorical Figures NAACL 2024 The Empirical Variability of Narrative Perceptions of Social Media Texts EMNLP 2024 The Fall of ROME: Understanding the Collapse of LLMs in Model Editing EMNLP 2024 The Fundamental Limits of Least-Privilege Learning ICML 2024 The Generative AI Paradox in Evaluation: “What It Can Solve, It May Not Evaluate” EACL 2024 The Generative AI Paradox: “What It Can Create, It May Not Understand” ICLR 2024 The Good, The Bad, and Why: Unveiling Emotions in Generative AI ICML 2024 The Guidelines Specialists at FIGNEWS 2024 Shared Task: An annotation guideline to Unravel Bias in News Media Narratives Using a Linguistic Approach ACL 2024 The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models ACL 2024 The Illusion of Competence: Evaluating the Effect of Explanations on Users’ Mental Models of Visual Question Answering Systems EMNLP 2024 The Impact of Integration Step on Integrated Gradients EACL 2024 The Instinctive Bias: Spurious Images lead to Illusion in MLLMs EMNLP 2024 The Intelligible and Effective Graph Neural Additive Network NeurIPS 2024 The Key Points: Using Feature Importance to Identify Shortcomings in Sign Language Recognition Models COLING 2024 The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI EMNLP 2024 The Linear Representation Hypothesis and the Geometry of Large Language Models ICML 2024 The Logic of Doxastic Strategies AAAI 2024 The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes CVPR 2024 Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability EMNLP 2024 Theoretical and Empirical Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Open-World Scenarios COLING 2024 The PetShop Dataset — Finding Causes of Performance Issues across Microservices CLeaR 2024