5 papers
TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
Xiaosong Han, Ke Chen, Xindi Dai +7
In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. Ho…
Holder Policy Optimisation
Yuxiang Chen, Dingli Liang, Yihang Chen +8
Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mapping these trajectory-level ad…
DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning
Xiaoyu Liu, Xiaoyu Guan, Di Liang +1
Supervised fine-tuning (SFT) is a crucial step for adapting large language models (LLMs) to downstream tasks. However, conflicting objectives across heterogeneous SFT tasks often i…
DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF
Ziyuan Gao, Di Liang, Xianjie Wu +2
Existing reinforcement learning methods for Chain-of-Thought reasoning suffer from two critical limitations. First, they operate as monolithic black boxes that provide undifferenti…
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
Yao Wang, Di Liang, Minlong Peng
Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'',…