hidden state

HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States ACL 2025 Hidden No More: Attacking and Defending Private Third-Party LLM Inference ICML 2025 Hopscotch: Discovering and Skipping Redundancies in Language Models EMNLP 2025 ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs ACL 2025 Improving Language Model Distillation through Hidden State Matching ICLR 2025 Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations EMNLP 2025 InnerThoughts: Disentangling Representations and Predictions in Large Language Models AISTATS 2025 Internal Chain-of-Thought: Empirical Evidence for Layer‐wise Subtask Scheduling in LLMs EMNLP 2025 Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness ICLR 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering ACL 2025 Language Dominance in Multilingual Large Language Models EMNLP 2025 Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation ICLR 2025 Linear Steerability in Language Models: When It Emerges and How It Evolves EMNLP 2025 LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement ICLR 2025 Measuring In-Context Computation Complexity via Hidden State Prediction ICML 2025 Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel ACL 2025 Neural Wave Equation for Irregularly Sampled Sequence Data ICLR 2025 NLP_CIMAT at SemEval-2025 Task 3: Just Ask GPT or look Inside. A prompt and Neural Networks Approach to Hallucination Detection SemEval 2025 OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference ICML 2025 Probing for Arithmetic Errors in Language Models EMNLP 2025 RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations ICML 2025 SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models AAAI 2025 ShieldHead: Decoding-time Safeguard for Large Language Models ACL 2025 Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation EMNLP 2025