Interpretability

Toward Efficient Sparse Autoencoder-Guided Steering for Improved In-Context Learning in Large Language Models EMNLP 2025 Toward Machine Translation Literacy: How Lay Users Perceive and Rely on Imperfect Translations EMNLP 2025 Towards Achieving Concept Completeness for Textual Concept Bottleneck Models EMNLP 2025 Towards an Explainable Comparison and Alignment of Feature Embeddings ICML 2025 Towards A “Novel” Benchmark: Evaluating Literary Fiction with Large Language Models ACL 2025 Towards Attributions of Input Variables in a Coalition ICML 2025 Towards a Unified and Verified Understanding of Group-Operation Networks ICLR 2025 Towards a Unified Paradigm of Concept Editing in Large Language Models EMNLP 2025 Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content CVPR 2025 Towards Automated Knowledge Integration From Human-Interpretable Representations ICLR 2025 Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks IJCAI 2025 Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning COLING 2025 Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach ACL 2025 Towards Explainable Hate Speech Detection ACL 2025 Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Framework ACL 2025 Towards Fair Representation: Clustering and Consensus COLT 2025 Towards Faithful Multi-step Reasoning through Fine-Grained Causal-aware Attribution Reasoning Distillation COLING 2025 Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models EMNLP 2025 Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition CVPR 2025 Towards flexible perception with visual memory ICML 2025 Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception ACL 2025 Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models ICML 2025 Towards Human-Understandable Multi-Dimensional Concept Discovery CVPR 2025 Towards Human Understanding of Paraphrase Types in Large Language Models COLING 2025 Towards Interpreting Visual Information Processing in Vision-Language Models ICLR 2025