activity
20192023
most citedMulti-Task Deep Neural Networks for Natural Language Understanding

221 citations · 742 across the 17 of their papers we have counts for

collaborators
Showing cs.CLShow all

25 papers · 1 filter

cs.CL202319 cited

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

Yixiao Li, Yifan Yu, Chen Liang +4

Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario wher…

cs.CL2023

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective

Ming Zhong, Chenxin An, Weizhu Chen +2

Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operati…

cs.CL2023

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Yung-Sung Chuang, Yujia Xie, Hongyin Luo +3

Despite their impressive capabilities, large language models (LLMs) are prone to hallucinations, i.e., generating content that deviates from facts seen during pretraining. We propo…

cs.CL20232 cited

Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection

Zekun Li, Baolin Peng, Pengcheng He +1

Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following, becoming increasingly crucial across various applications. However, this capability…

cs.CL20232 cited

Interactive Editing for Text Summarization

Yujia Xie, Xun Wang, Si-Qing Chen +2

Summarizing lengthy documents is a common and essential task in our daily lives. Although recent advancements in neural summarization models can assist in crafting general-purpose…

cs.CL20232 cited

Summarization with Precise Length Control

Lesly Miculicich, Yujia Xie, Song Wang +1

Many applications of text generation such as summarization benefit from accurately controlling the text length. Existing approaches on length-controlled summarization either result…