29 citations · 163 across the 56 of their papers we have counts for
13 papers · 1 filter
Improving Large Models with Small models: Lower Costs and Better Performance
Dong Chen, Shuo Zhang, Yueting Zhuang +4
Pretrained large models (PLMs), such as ChatGPT, have demonstrated remarkable performance across diverse tasks. However, the significant computational requirements of PLMs have dis…
DuetRAG: Collaborative Retrieval-Augmented Generation
Dian Jiao, Li Cai, Jingsheng Huang +3
Retrieval-Augmented Generation (RAG) methods augment the input of Large Language Models (LLMs) with relevant retrieved passages, reducing factual errors in knowledge-intensive task…
I3: Intent-Introspective Retrieval Conditioned on Instructions
Kaihang Pan, Juncheng Li, Wenjie Wang +7
Recent studies indicate that dense retrieval models struggle to perform well on a wide variety of retrieval tasks that lack dedicated training data, as different retrieval tasks of…
SkillQG: Learning to Generate Question for Reading Comprehension Assessment
Xiaoqiang Wang, Bang Liu, Siliang Tang +1
We present $\textbf{$\texttt{SkillQG}$}$: a question generation framework with controllable comprehension types for assessing and improving machine reading comprehension models. Ex…
Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document
Xiangnan Chen, Qian Xiao, Juncheng Li +4
Visual Relation Extraction (VRE) is a powerful means of discovering relationships between entities within visually-rich documents. Existing methods often focus on manipulating enti…
Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization
Kaihang Pan, Juncheng Li, Hongye Song +3
Prompt tuning is a parameter-efficient method, which learns soft prompts and conditions frozen language models to perform specific downstream tasks. Though effective, prompt tuning…
SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference
Boren Hu, Yun Zhu, Jiacheng Li +1
Dynamic early exiting has been proven to improve the inference speed of the pre-trained language model like BERT. However, all samples must go through all consecutive layers before…
A Study on ReLU and Softmax in Transformer
Kai Shen, Junliang Guo, Xu Tan +3
The Transformer architecture consists of self-attention and feed-forward networks (FFNs) which can be viewed as key-value memories according to previous works. However, FFN and tra…
Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning
Wenbin An, Feng Tian, Ping Chen +3
Novel category discovery aims at adapting models trained on known categories to novel categories. Previous works only focus on the scenario where known and novel categories are of…
QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance
Xiaoqiang Wang, Bang Liu, Siliang Tang +1
Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input context of generation, rendering the lack of…
Feeding What You Need by Understanding What You Learned
Xiaoqiang Wang, Bang Liu, Fangli Xu +3
Machine Reading Comprehension (MRC) reveals the ability to understand a given text passage and answer questions based on it. Existing research works in MRC rely heavily on large-si…
CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
Tao Chen, Haizhou Shi, Siliang Tang +3
The journey of reducing noise from distant supervision (DS) generated training data has been started since the DS was first introduced into the relation extraction (RE) task. For t…
Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training
Tao Chen, Haochen Shi, Liyuan Liu +4
With recent advances in distantly supervised (DS) relation extraction (RE), considerable attention is attracted to leverage multi-instance learning (MIL) to distill high-quality su…