27 papers · 1 filter
De-attribute to Forget for LLM Unlearning
Xinyang Lu, Jiabao Pan, Rachael Hwee Ling Sim +3
The rapid development of large language models (LLMs) has raised concerns on the use of inappropriate data for training, which has led to a growing interest in LLM unlearning. Many…
ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning
Wenyang Hu, Junxiang Jia, Zhen Shu +3
Reinforcement Learning with Verifiable Rewards (RLVR) for language-model reasoning can fail at both extremes of task difficulty: easy prompts often produce all-correct, low-diversi…
BarrierSteer: LLM Safety via Learning Barrier Steering
Thanh Q. Tran, Arun Verma, Kiwan Wong +3
Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe content generation remains a significant…
BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks
Ruth Wan Theng Chew, Zhiliang Chen, Apivich Hemachandra +1
Optimization of LLM training and inference configurations, such as hyperparameters, data mixtures, and prompts, is critical to performance, but it is often approached heuristically…
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
Xiaoqiang Lin, Arun Verma, Zhongxiang Dai +3
The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answe…
Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibration
Manh Cuong Dao, Quang Hung Pham, Phi Le Nguyen +3
Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre-trained transformers do not hav…