most citedKnowledge Fusion of Large Language Models

8 citations · 9 across the 3 of their papers we have counts for

collaborators

9 papers

cs.CL2024

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…

cs.CL2024

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…

cs.CL2024

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.…

cs.CL20241 cited

Retrieval is Accurate Generation

Bowen Cao, Deng Cai, Leyang Cui +4

Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a co…

cs.CL20248 cited

Knowledge Fusion of Large Language Models

Fanqi Wan, Xinting Huang, Deng Cai +3

While training large language models (LLMs) from scratch can generate models with distinct functionalities and strengths, it comes at significant costs and may result in redundant…

cs.CL2024

Inferflow: an Efficient and Highly Configurable Inference Engine for Large Language Models

Shuming Shi, Enbo Zhao, Deng Cai +3

We present Inferflow, an efficient and highly configurable inference engine for large language models (LLMs). With Inferflow, users can serve most of the common transformer models…