57 citations · 178 across the 16 of their papers we have counts for
18 papers
Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability
Zhenting Huang, Junnan Liu, Qianren Mao +2
Sparse autoencoders (SAEs) are increasingly scaled to wider dictionaries to recover fine-grained structure from large language model activations. However, a feature is useful for i…
XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation
Qili Zhang, Qianren Mao, Yangyifei Luo +15
Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs), ensuring that the generated output…
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
Tianyu Cui, Yanling Wang, Chuanpu Fu +13
Large language models (LLMs) have strong capabilities in solving diverse natural language processing tasks. However, the safety and security issues of LLM systems have become the m…
Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
Yansong Li, Zhixing Tan, Paula Branco +1
Parameter-Efficient Fine-Tuning (PEFT) provides a practical way for users to customize Large Language Models (LLMs) with their private data in LLM service scenarios. However, the i…
Black-box Prompt Tuning with Subspace Learning
Yuanhang Zheng, Zhixing Tan, Peng Li +1
Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large…
A Template-based Method for Constrained Neural Machine Translation
Shuo Wang, Peng Li, Zhixing Tan +3
Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performan…
A Roadmap for Big Model
Sha Yuan, Hanyu Zhao, Shuai Zhao +97
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm. Researchers have achieved various outcomes in the c…
Integrating Vectorized Lexical Constraints for Neural Machine Translation
Shuo Wang, Zhixing Tan, Yang Liu
Lexically constrained neural machine translation (NMT), which controls the generation of NMT models with pre-specified constraints, is important in many practical scenarios. Due to…
MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
Zhixing Tan, Xiangwen Zhang, Shuo Wang +1
Prompting has recently been shown as a promising approach for applying pre-trained language models to perform downstream tasks. We present Multi-Stage Prompting (MSP), a simple and…
Language Models are Good Translators
Shuo Wang, Zhaopeng Tu, Zhixing Tan +3
Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of la…
CPM-2: Large-scale Cost-effective Pre-trained Language Models
Zhengyan Zhang, Yuxian Gu, Xu Han +16
In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-…
On the Language Coverage Bias for Neural Machine Translation
Shuo Wang, Zhaopeng Tu, Zhixing Tan +3
Language coverage bias, which indicates the content-dependent differences between sentence pairs originating from the source and target languages, is important for neural machine t…
Molecule Generation by Principal Subgraph Mining and Assembling
Xiangzhe Kong, Wenbing Huang, Zhixing Tan +1
Molecule generation is central to a variety of applications. Current attention has been paid to approaching the generation task as subgraph prediction and assembling. Nevertheless,…
Dynamic Multi-Branch Layers for On-Device Neural Machine Translation
Zhixing Tan, Zeyuan Yang, Meng Zhang +3
With the rapid development of artificial intelligence (AI), there is a trend in moving AI applications, such as neural machine translation (NMT), from cloud to mobile devices. Cons…
Neural Machine Translation: A Review of Methods, Resources, and Tools
Zhixing Tan, Shuo Wang, Zonghan Yang +4
Machine translation (MT) is an important sub-field of natural language processing that aims to translate natural languages using computers. In recent years, end-to-end neural machi…
Towards Linear Time Neural Machine Translation with Capsule Networks
Mingxuan Wang, Jun Xie, Zhixing Tan +3
In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as \textsc{CapsNMT}. \textsc{CapsNMT} us…
Deep Semantic Role Labeling with Self-Attention
Zhixing Tan, Mingxuan Wang, Jun Xie +2
Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end SRL with recurrent neural…
Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation
Jinsong Su, Zhixing Tan, Deyi Xiong +3
Neural machine translation (NMT) heavily relies on word-level modelling to learn semantic representations of input sentences. However, for languages without natural word delimiters…