conftrace_

reward-guided decoding

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

decoding time (1) personalized decoding (1) safe decoding (1) large language model (1) controlled decoding (1) user preference (1) object hallucination (1) test-time alignment (1) jailbreak attack (1) multimodal large language model (1)

Papers

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation ACL 2026 Controlling Multimodal LLMs via Reward-guided Decoding ICCV 2025 Personalized LLM Decoding via Contrasting Personal Preference EMNLP 2025