Home
People
Events
Research
Publications
Contact
News
LLM
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction …
Ming Li
,
Yong Zhang
,
Shwai He
,
Zhitao Li
,
Hongyu Zhao
,
Jianzong Wang
,
Ning Cheng
,
Tianyi Zhou
Cite
Code
arXiv
QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically …
Sheng Ouyang
,
Jianzong Wang
,
Yong Zhang
,
Zhitao Li
,
Ziqi Liang
,
Xulong Zhang
,
Ning Cheng
,
Jing Xiao
Cite
arXiv
IEEE
From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
In the realm of Large Language Models, the balance between instruction data quality and quantity has become a focal point. Recognizing …
Ming Li
,
Yong Zhang
,
Zhitao Li
,
Jiuhai Chen
,
Lichang Chen
,
Ning Cheng
,
Jianzong Wang
,
Tianyi Zhou
,
Jing Xiao
Cite
Code
arXiv
INCPrompt: Task-Aware Incremental Prompting for Rehearsal-Free Class-incremental Learning
This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. …
Zhiyuan Wang
,
Xiaoyang Qu
,
Jing Xiao
,
Bokui Chen
,
Jianzong Wang
Cite
arXiv
IEEE
Leveraging Biases in Large Language Models: bias-kNN for Effective Few-Shot Learning
Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning. …
Yong Zhang
,
Hanzhang Li
,
Zhitao Li
,
Ning Cheng
,
Ming Li
,
Jing Xiao
,
Jianzong Wang
Cite
arXiv
IEEE
P2DT: Mitigating Forgetting in Task-Incremental Learning with Progressive Prompt Decision Transformer
Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance …
Zhiyuan Wang
,
Xiaoyang Qu
,
Jing Xiao
,
Bokui Chen
,
Jianzong Wang
Cite
arXiv
IEEE
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models
Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains …
Tong Ye
,
Shijing Si
,
Jianzong Wang
,
Ning Cheng
,
Zhitao Li
,
Jing Xiao
PDF
Cite
arXiv
AAAI
PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter
The Retrieval Question Answering (ReQA) task employs the retrieval-augmented framework, composed of a retriever and generator. The …
Haoyan Yang
,
Zhitao Li
,
Yong Zhang
,
Jianzong Wang
,
Ning Cheng
,
Ming Li
,
Jing Xiao
PDF
Cite
arXiv
ACL
Sparks of Large Audio Models: A Survey and Outlook
This survey paper provides a comprehensive overview of the recent advancements and challenges in applying large language models to the …
Siddique Latif
,
Moazzam Shoukat
,
Fahad Shamshad
,
Muhammad Usama
,
Yi Ren
,
Heriberto Cuayáhuitl
,
Wenwu Wang
,
Xulong Zhang
,
Roberto Togneri
,
Björn W. Schuller
Cite
Code
arXiv
Prompt Guided Copy Mechanism for Conversational Question Answering
Conversational Question Answering (CQA) is a challenging task that aims to generate natural answers for conversational flow questions. …
Yong Zhang
,
Zhitao Li
,
Jianzong Wang
,
Yiming Gao
,
Ning Cheng
,
Fengying Yu
,
Jing Xiao
PDF
Cite
arXiv
ISCA
»
Cite
×