activity
20192023
most citedERNIE: Enhanced Representation through Knowledge Integration

773 citations · 1.1k across the 11 of their papers we have counts for

collaborators
Showing cs.CLShow all

15 papers · 1 filter

cs.CL2023

Tool-Augmented Reward Modeling

Lei Li, Yekun Chai, Shuohuan Wang +4

Reward modeling (a.k.a., preference modeling) is instrumental for aligning large language models with human preferences, particularly within the context of reinforcement learning f…

cs.CL2023

Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation

Ruiyang Ren, Yuhao Wang, Yingqi Qu +6

Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge. However, it remains unclear how well LLMs are able to perceive the…

cs.CL20221 cited

Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards

Yekun Chai, Shuohuan Wang, Yu Sun +3

Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did n…

cs.CL20226 cited

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding

Qiming Peng, Yinxu Pan, Wenjin Wang +12

Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and u…

cs.CL202219 cited

ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval

Yuxiang Lu, Yiding Liu, Jiaxiang Liu +8

Neural retrievers based on pre-trained language models (PLMs), such as dual-encoders, have achieved promising performance on the task of open-domain question answering (QA). Their…

cs.CL20226 cited

ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention

Yang Liu, Jiaxiang Liu, Li Chen +7

Sparse Transformer has recently attracted a lot of attention since the ability for reducing the quadratic dependency on the sequence length. We argue that two factors, information…