conftrace_

token logit

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) avoidance decoding (1) trajectory rollout (1) repetition reduction (1) hallucinations (1) q-value (1) early layer activations (1) lvlms (1) gradient-free (1) text degeneration (1)

Papers

Avoidance Decoding for Diverse Multi-Branch Story Generation EMNLP 2025 Enhancing Decision-Making of Large Language Models via Actor-Critic ICML 2025 The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering ICML 2025 Toxicity Detection for Free NeurIPS 2024