decoding strategy

Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization ACL 2026 Breaking the Illusion: When Positive Meets Negative in Multimodal Decoding CVPR 2026 Confidence Should Be Calibrated More Than One Turn Deep ACL 2026 Empirical Analysis of Decoding Biases in Masked Diffusion Models ACL 2026 Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation AAAI 2026 Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics ACL 2026 Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models CVPR 2026 Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought CVPR 2026 Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance CVPR 2026 VCGD: Visual Clue Guided Decoding with Caption Model for Mitigating Hallucination in Multimodal Large Language Models AAAI 2026 When to Think and When to Look: Uncertainty-Guided Lookback CVPR 2026 Avoidance Decoding for Diverse Multi-Branch Story Generation EMNLP 2025 Better Instruction-Following Through Minimum Bayes Risk ICLR 2025 Choice is what matters after Attention AISTATS 2025 CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation ACL 2025 DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models ICLR 2025 Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts ACL 2025 DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations EMNLP 2025 DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability EMNLP 2025 DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models EMNLP 2025 Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model ACL 2025 ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation EMNLP 2025 G2: Guided Generation for Enhanced Output Diversity in LLMs EMNLP 2025 Genre Matters: How Text Types Interact with Decoding Strategies and Lexical Predictors in Shaping Reading Behavior EMNLP 2025 GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation EMNLP 2025