Interpretability

None of the Above, Less of the Right Parallel Patterns in Human and LLM Performance on Multi-Choice Questions Answering ACL 2025 Non-Existent Relationship: Fact-Aware Multi-Level Machine-Generated Text Detection EMNLP 2025 Nonlinear multiregion neural dynamics with parametric impulse response communication channels ICLR 2025 Nonparametric Identification of Latent Concepts ICML 2025 No Questions are Stupid, but some are Poorly Posed: Understanding Poorly-Posed Information-Seeking Questions ACL 2025 Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attributions Explainability ACL 2025 NormalLoc: Visual Localization on Textureless 3D Models using Surface Normals ICCV 2025 Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes AAAI 2025 NormXLogit: The Head-on-Top Never Lies EMNLP 2025 Not All Language Model Features Are One-Dimensionally Linear ICLR 2025 Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks ICML 2025 Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models EMNLP 2025 Not Lost After All: How Cross-Encoder Attribution Challenges Position Bias Assumptions in LLM Summarization EMNLP 2025 Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models CVPR 2025 Not ready for the bench: LLM legal interpretation is unstable and uncalibrated to human judgments EMNLP 2025 NovAScore: A New Automated Metric for Evaluating Document Level Novelty COLING 2025 NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models ICLR 2025 NSF-MAP: Neurosymbolic Multimodal Fusion for Robust and Interpretable Anomaly Prediction in Assembly Pipelines IJCAI 2025 Nuance Matters: Probing Epistemic Consistency in Causal Reasoning AAAI 2025 Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection CVPR 2025 OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad CVPR 2025 Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding CVPR 2025 ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction ICCV 2025 OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens ACL 2025 o-MEGA: Optimized Methods for Explanation Generation and Analysis EMNLP 2025