Interpretability

Understanding Faithfulness and Reasoning of Large Language Models on Plain Biomedical Summaries EMNLP 2024 Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure NeurIPS 2024 Understanding Information Storage and Transfer in Multi-Modal Large Language Models NeurIPS 2024 Understanding Inter-Concept Relationships in Concept-Based Models ICML 2024 Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models Interspeech 2024 Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense NAACL 2024 Understanding Video Transformers via Universal Concept Discovery CVPR 2024 UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation NeurIPS 2024 Unified Evidence Enhancement Inference Framework for Fake News Detection IJCAI 2024 Unified Hallucination Detection for Multimodal Large Language Models ACL 2024 UniSumEval: Towards Unified, Fine-grained, Multi-dimensional Summarization Evaluation for LLMs EMNLP 2024 United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories NeurIPS 2024 Unleashing Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation NeurIPS 2024 Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding EMNLP 2024 Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models EMNLP 2024 Unlocking the Potential of Large Language Models for Clinical Text Anonymization: A Comparative Study ACL 2024 Unraveling Pain Levels: A Data-Uncertainty Guided Approach for Effective Pain Assessment AAAI 2024 Unsegment Anything by Simulating Deformation CVPR 2024 Unsupervised Concept Discovery Mitigates Spurious Correlations ICML 2024 Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models ACL 2024 Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration ICML 2024 Unveiling and Manipulating Prompt Influence in Large Language Models ICLR 2024 Unveiling Divergent Inductive Biases of LLMs on Temporal Data NAACL 2024 Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons EMNLP 2024 Unveiling Implicit Deceptive Patterns in Multi-Modal Fake News via Neuro-Symbolic Reasoning AAAI 2024