Interpretability

SocREval: Large Language Models with the Socratic Method for Reference-free Reasoning Evaluation NAACL 2024 SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models ICLR 2024 SPADE: Sparsity-Guided Debugging for Deep Neural Networks ICML 2024 Spanning the Spectrum of Hatred Detection: A Persian Multi-Label Hate Speech Dataset with Annotator Rationales AAAI 2024 Sparse and Faithful Explanations Without Sparse Models AISTATS 2024 Sparse and Structured Hopfield Networks ICML 2024 Sparse Autoencoders Find Highly Interpretable Features in Language Models ICLR 2024 Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications ICML 2024 Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention AAAI 2024 Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication NeurIPS 2024 Spectral Editing of Activations for Large Language Model Alignment NeurIPS 2024 Split and Merge: Aligning Position Biases in LLM-based Evaluators EMNLP 2024 Spotting AI’s Touch: Identifying LLM-Paraphrased Spans in Text ACL 2024 SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models EACL 2024 StackSight: Unveiling WebAssembly through Large Language Models and Neurosymbolic Chain-of-Thought Decompilation ICML 2024 STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering AAAI 2024 Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning COLING 2024 STAR: SocioTechnical Approach to Red Teaming Language Models EMNLP 2024 Stealing part of a production language model ICML 2024 Steering Llama 2 via Contrastive Activation Addition ACL 2024 Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter? EMNLP 2024 Step Feasibility-Aware and Error-Correctable Entailment Tree Generation COLING 2024 STL: Still Tricky Logic (for System Validation, Even When Showing Your Work) NeurIPS 2024 Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution NeurIPS 2024 Stochastic Concept Bottleneck Models NeurIPS 2024