Skip to content
conftrace_

token-level optimization

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) preference optimization (4) language model (3) reinforcement learning from human feedback (2) language model alignment (2) knowledge distillation (2) direct preference optimization (2) reinforcement learning (2) logit extrapolation (1) advantage clipping (1)

Papers

Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech ACL 2026 LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models AAAI 2026 MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs AAAI 2026 Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning Model AAAI 2026 AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation ACL 2025 Token-level Preference Self-Alignment Optimization for Multi-style Outline Controllable Generation ACL 2025 Token-level Proximal Policy Optimization for Query Generation EMNLP 2025 Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training ACL 2025 TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation EMNLP 2025 Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization NeurIPS 2024 Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data EMNLP 2024