Interpretability

SMoSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks AAAI 2025 SmurfCat at SemEval-2025 Task 3: Bridging External Knowledge and Model Uncertainty for Enhanced Hallucination Detection SemEval 2025 Sneaking Syntax into Transformer Language Models with Tree Regularization NAACL 2025 SocialEval: Evaluating Social Intelligence of Large Language Models ACL 2025 Social Genome: Grounded Social Reasoning Abilities of Multimodal Models EMNLP 2025 Soft Local Completeness: Rethinking Completeness in XAI ICCV 2025 SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels ICML 2025 Source Attribution for Large Language Models IJCNLP 2025 SPaRC: A Spatial Pathfinding Reasoning Challenge EMNLP 2025 Sparse Activation Editing for Reliable Instruction Following in Narratives EMNLP 2025 Sparse Autoencoder Features for Classifications and Transferability EMNLP 2025 Sparse Autoencoders Do Not Find Canonical Units of Analysis ICLR 2025 Sparse Autoencoders for Hypothesis Generation ICML 2025 Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models ICLR 2025 Sparse components distinguish visual pathways & their alignment to neural networks ICLR 2025 Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models ICLR 2025 Sparse Latents Steer Retrieval-Augmented Generation ACL 2025 Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs EMNLP 2025 Spatial Representation of Large Language Models in 2D Scene ACL 2025 Specifying What You Know or Not for Multi-Label Class-Incremental Learning AAAI 2025 Spectral Insights into Data-Oblivious Critical Layers in Large Language Models ACL 2025 Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds Interspeech 2025 Speech Act Patterns for Improving Generalizability of Explainable Politeness Detection Models ACL 2025 Speech Reference Intervals: An Assessment of Feasibility in Depression Symptom Severity Prediction Interspeech 2025 SpeHeaTal: A Cluster-Enhanced Segmentation Method for Sperm Morphology Analysis AAAI 2025