Interpretability

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations ICCV 2025 Graph-Guided Textual Explanation Generation Framework EMNLP 2025 Graph Inverse Style Transfer for Counterfactual Explainability ICML 2025 GraphNarrator: Generating Textual Explanations for Graph Neural Networks ACL 2025 Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation EMNLP 2025 GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models IJCAI 2025 Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural Networks AAAI 2025 Great Memory, Shallow Reasoning: Limits of kNN-LMs NAACL 2025 Grounding Methods for Neural-Symbolic AI IJCAI 2025 Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups EMNLP 2025 GSBA^K: top-K Geometric Score-based Black-box Attack ICLR 2025 GSE: Group-wise Sparse and Explainable Adversarial Attacks ICLR 2025 GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models EMNLP 2025 Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms ICML 2025 Gumbel Counterfactual Generation From Language Models ICLR 2025 G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o AAAI 2025 HaDeMiF: Hallucination Detection and Mitigation in Large Language Models ICLR 2025 HalLoc: Token-level Localization of Hallucinations for Vision Language Models CVPR 2025 HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead NAACL 2025 Hallucinated Span Detection with Multi-View Attention Features EMNLP 2025 Hallucination Detection in LLMs Using Spectral Features of Attention Maps EMNLP 2025 Hallucination Detection in Structured Query Generation via LLM Self-Debating EMNLP 2025 Hallucination Detectives at SemEval-2025 Task 3: Span-Level Hallucination Detection for LLM-Generated Answers SemEval 2025 Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training ACL 2025 Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics IJCNLP 2025