Interpretability

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning EMNLP 2025 SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models ICLR 2025 SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness WACV 2025 Sarcasm-R1: Enhancing Sarcasm Detection through Focused Reasoning EMNLP 2025 Saudi-Alignment Benchmark: Assessing LLMs Alignment with Cultural Norms and Domain Knowledge in the Saudi Context EMNLP 2025 Scalable Influence and Fact Tracing for Large Language Model Pretraining ICLR 2025 Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization IJCAI 2025 Scalable Solutions for Decision-Making Systems Using Explainable Policy Representations AAAI 2025 Scaling and evaluating sparse autoencoders ICLR 2025 Scaling Effects on Latent Representation Edits in GPT Models (Student Abstract) AAAI 2025 Scaling Sparse Feature Circuits For Studying In-Context Learning ICML 2025 SCALM: Detecting Bad Practices in Smart Contracts Through LLMs AAAI 2025 ScamNet: Toward Explainable Large Language Model-Based Fraudulent Shopping Website Detection AAAI 2025 S-CFE: Simple Counterfactual Explanations AISTATS 2025 SciBERT Meets Contrastive Learning: A Solution for Scientific Hallucination Detection ACL 2025 SciHallu: A Multi-Granularity Hallucination Detection Dataset for Scientific Writing IJCNLP 2025 SCIURus: Shared Circuits for Interpretable Uncertainty Representations in Language Models NAACL 2025 SCOP: Evaluating the Comprehension Process of Large Language Models from a Cognitive View ACL 2025 Score-based Pullback Riemannian Geometry: Extracting the Data Manifold Geometry using Anisotropic Flows ICML 2025 SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models NAACL 2025 Seeing Eye to AI: Comparing Human Gaze and Model Attention in Video Memorability WACV 2025 Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models EMNLP 2025 Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Models EMNLP 2025 Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection ICCV 2025 Seeing Through the Mask: AI-Generated Text Detection with Similarity-Guided Graph Reasoning IJCNLP 2025