Interpretability

Extracting Linguistic Information from Large Language Models: Syntactic Relations and Derivational Knowledge EMNLP 2025 Extracting PAC Decision Trees from Black Box Binary Classifiers: The Gender Bias Study Case on BERT-based Language Models AAAI 2025 Extracting structure from an LLM - how to improve on surprisal-based models of Human Language Processing COLING 2025 Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass EMNLP 2025 Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts ICML 2025 Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models ICML 2025 FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models EMNLP 2025 FACTCHECKMATE: Preemptively Detecting and Mitigating Hallucinations in LMs EMNLP 2025 FactLens: Benchmarking Fine-Grained Fact Verification ACL 2025 Factor Graph-based Interpretable Neural Networks ICLR 2025 Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion ACL 2025 FACTS&EVIDENCE: An Interactive Tool for Transparent Fine-Grained Factual Verification of Machine-Generated Text NAACL 2025 FADE: Why Bad Descriptions Happen to Good Features ACL 2025 FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering ACL 2025 FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs NAACL 2025 FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows" ICLR 2025 Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint AAAI 2025 FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Datasets Dependency ACL 2025 FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models ICLR 2025 FarExStance: Explainable Stance Detection for Farsi COLING 2025 Fast Explanations via Policy Gradient-Optimized Explainer IJCAI 2025 FastJSMA: Accelerating Jacobian-based Saliency Map Attacks through Gradient Decoupling ICCV 2025 FEAT-KD: Learning Concise Representations for Single and Multi-Target Regression via TabNet Knowledge Distillation ICML 2025 Feature Clipping for Uncertainty Calibration AAAI 2025 Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models EMNLP 2025