inference-time intervention

AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM CVPR 2026 Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models AAAI 2026 Dissecting Failure Dynamics in Large Language Model Reasoning ACL 2026 Improving Chain-of-Thought for Logical Reasoning via Attention-Aware Intervention EACL 2026 Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society ACL 2026 LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction AAAI 2026 Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering AAAI 2026 Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy ACL 2026 Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation AAAI 2026 Steering Large Language Models for Machine Translation Personalization EACL 2026 Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time Interventions EACL 2026 VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck ACL 2026 Automating Steering for Safe Multimodal Large Language Models EMNLP 2025 Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering ACL 2025 Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation NAACL 2025 Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs EMNLP 2025 Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression EMNLP 2025 Mitigating Language Confusion through Inference-time Intervention COLING 2025 Multi-Attribute Steering of Language Models via Targeted Intervention ACL 2025 Neuron-Level Differentiation of Memorization and Generalization in Large Language Models EMNLP 2025 Probe-Free Low-Rank Activation Intervention NAACL 2025 Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering NAACL 2025 Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models ACL 2025 Analysing the Generalisation and Reliability of Steering Vectors NeurIPS 2024 Non-Linear Inference Time Intervention: Improving LLM Truthfulness Interspeech 2024