5 papers · 1 filter
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
Chang Gao, Haiyun Jiang, Deng Cai +2
Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other in…
Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
Sen Yang, Leyang Cui, Deng Cai +3
Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to select worth-annotating resp…
CORM: Cache Optimization with Recent Message for Large Language Model Inference
Jincheng Dai, Zhuowei Huang, Haiyun Jiang +4
Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources.…
Reasons to Reject? Aligning Language Models with Judgments
Weiwen Xu, Deng Cai, Zhisong Zhang +2
As humans, we consistently interact with our peers and receive feedback in the form of natural language. This language feedback allows us to maintain appropriate behavior, and rect…
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction
Tingchen Fu, Deng Cai, Lemao Liu +2
Supervised fine-tuning (SFT) on instruction-following corpus is a crucial approach toward the alignment of large language models (LLMs). However, the performance of LLMs on standar…