58 citations · 205 across the 130 of their papers we have counts for
22 papers · 1 filter
PFID: Privacy First Inference Delegation Framework for LLMs
Haoyan Yang, Zhitao Li, Yong Zhang +4
This paper introduces a novel privacy-preservation framework named PFID for LLMs that addresses critical privacy concerns by localizing user data through model sharding and singula…
Enhancing Emotion Recognition in Conversation through Emotional Cross-Modal Fusion and Inter-class Contrastive Learning
Haoxiang Shi, Xulong Zhang, Ning Cheng +4
The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple…
QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
Sheng Ouyang, Jianzong Wang, Yong Zhang +5
Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work intr…
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Ming Li, Yong Zhang, Shwai He +5
Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both…
Leveraging Biases in Large Language Models: "bias-kNN'' for Effective Few-Shot Learning
Yong Zhang, Hanzhang Li, Zhitao Li +4
Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning. However, their performance can be hampered by inhere…
PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter
Haoyan Yang, Zhitao Li, Yong Zhang +4
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The generator formulates the answer based on the docu…
Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism
Jiaxin Fan, Yong Zhang, Hanzhang Li +5
Chinese Automatic Speech Recognition (ASR) error correction presents significant challenges due to the Chinese language's unique features, including a large character set and borde…
Prompt Guided Copy Mechanism for Conversational Question Answering
Yong Zhang, Zhitao Li, Jianzong Wang +4
Conversational Question Answering (CQA) is a challenging task that aims to generate natural answers for conversational flow questions. In this paper, we propose a pluggable approac…
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
Ming Li, Yong Zhang, Zhitao Li +6
In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology f…
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models
Tong Ye, Shijing Si, Jianzong Wang +3
Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains challenging. Most dialog response retrieval models outp…
Efficient Uncertainty Estimation with Gaussian Process for Reliable Dialog Response Retrieval
Tong Ye, Zhitao Li, Jianzong Wang +2
Deep neural networks have achieved remarkable performance in retrieval-based dialogue systems, but they are shown to be ill calibrated. Though basic calibration methods like Monte…
Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition
Xulong Zhang, Jianzong Wang, Ning Cheng +3
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic in…
Improving Imbalanced Text Classification with Dynamic Curriculum Learning
Xulong Zhang, Jianzong Wang, Ning Cheng +1
Recent advances in pre-trained language models have improved the performance for text classification tasks. However, little attention is paid to the priority scheduling strategy on…
Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition
Chendong Zhao, Jianzong Wang, Wen qi Wei +3
The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). Howe…
Blur the Linguistic Boundary: Interpreting Chinese Buddhist Sutra in English via Neural Machine Translation
Denghao Li, Yuqiao Zeng, Jianzong Wang +5
Buddhism is an influential religion with a long-standing history and profound philosophy. Nowadays, more and more people worldwide aspire to learn the essence of Buddhism, attachin…
Adaptive Activation Network For Low Resource Multilingual Speech Recognition
Jian Luo, Jianzong Wang, Ning Cheng +2
Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly e…
Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information
Shijing Si, Jianzong Wang, Ruiyi Zhang +2
Non-negative matrix factorization (NMF) based topic modeling is widely used in natural language processing (NLP) to uncover hidden topics of short text documents. Usually, training…
Federated Split BERT for Heterogeneous Text Classification
Zhengyang Li, Shijing Si, Jianzong Wang +1
Pre-trained BERT models have achieved impressive performance in many natural language processing (NLP) tasks. However, in many real-world situations, textual data are usually decen…
Self-Attention for Incomplete Utterance Rewriting
Yong Zhang, Zhitao Li, Jianzong Wang +2
Incomplete utterance rewriting (IUR) has recently become an essential task in NLP, aiming to complement the incomplete utterance with sufficient context information for comprehensi…
VU-BERT: A Unified framework for Visual Dialog
Tong Ye, Shijing Si, Jianzong Wang +3
The visual dialog task attempts to train an agent to answer multi-turn questions given an image, which requires the deep understanding of interactions between the image and dialog…
Joint Intent Detection And Slot Filling Based on Continual Learning Model
Yanfei Hui, Jianzong Wang, Ning Cheng +3
Slot filling and intent detection have become a significant theme in the field of natural language understanding. Even though slot filling is intensively associated with intent det…
Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages
Cheng Yi, Jianzhong Wang, Ning Cheng +2
There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled…