Rui Li

Rui Li

Auto-generated profile, based on publicly available information

Rui Li

Inspur Academy of Science and Technology, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 December 2023
Verified
Conference Paper
Open access
ZWZizhong Wei
Zizhong Wei
DGDongsheng Guo
Dongsheng Guo
DHDengrong Huang
Dengrong Huang
QZQilai Zhang
Qilai Zhang
SZSijia Zhang
Sijia Zhang
RLRui Li
Rui Li
Large language models (LLMs) have achieved impressive success in generating fluent and coherent texts in natural language. However, the presence of inaccurate or low-quality data can unintentionally lead to the retention of incorrect knowledge, resulting in hallucinations that hinder progress in content generation. In this paper, we propose a comprehensive framework aimed at detecting and mitigating these hallucinations. Our approach uses Named Entity Recognition (NER) and Entity Relationship (ER) models to identify hallucination entities and sentences during the detection phase. Furthermore, by incorporating prompt engineering, we effectively correct these hallucination sentences using LLM in the mitigation phase. Tests on real articles confirm the effectiveness of our approach in rectifying LLM-associated hallucinations without adding new ones, thereby enhancing their reliability and credibility.

22 December 2023
Verified
Conference Paper
Open access
KJKai Jiang
Kai Jiang
QZQilai Zhang
Qilai Zhang
DGDongsheng Guo
Dongsheng Guo
DHDengrong Huang
Dengrong Huang
SZSijia Zhang
Sijia Zhang
RLRui Li
Rui Li
News generation, as a subset of long-form text generation task, is an important challenge in natural language processing. The creation of news articles necessitates a foundation in factual events, demanding the authenticity of content. The current large language models (LLMs) are capable of generating fluent text. However, these models often result in the generation of text that includes unfounded or inaccurate information, a phenomenon known as hallucinations. To ease this issue, we introduce a novel method. This approach leverages structured prompt-template inputs to guide the generation process, coupled with a post-checking module to ensure content authenticity. Furthermore, we propose two novel metrics, namely, topic consistency and core consistency, to evaluate the quality of the generated news. We have conducted extensive experiments using real news datasets, and our findings indicate that the proposed framework demonstrably mitigates the incidence of hallucinations in algorithmically generated news content, concurrently enhancing the overall quality of the produced news articles.

26 July 2024
Verified
Conference Paper
Open access
ZWZizhong Wei
Zizhong Wei
DHDengrong Huang
Dengrong Huang
JZJichen Zhang
Jichen Zhang
CSChen Song
Chen Song
SZSijia Zhang
Sijia Zhang
QDQiang Duan
Qiang Duan
Large language models (LLMs) possess exceptional capabilities, but their effectiveness is limited by their knowledge base. Retrieval-Augmented Generation (RAG) techniques integrate external knowledge to enhance performance in question-answering tasks. However, RAG techniques may encounter difficulties in dealing with irrelevant content, complex queries, as well as accurately evaluating the importance and relevance of information. To address these challenges, we developed an optimization question-answering system General Adaptive RAG (GARAG), specifically tailored for question-and-answer tasks. Our system utilizes a retrieval agent to identify relevant content and a generation agent to construct answers based on the question and retrieved information. Additionally, we incorporated modules for question complexity measurement, question correction, query transformation, query routing, and adaptive retrieval to improve intent recognition and document retrieval. We implemented an answer corrector and discriminator, as well as a self-reflection mechanism, to enhance output quality and factuality. Empirical experiments conducted on real-world questions validate the effectiveness of our question-and-answer system.

22 December 2023
Verified
Conference Paper
Open access
JZJichen Zhang
Jichen Zhang
QDQiang Duan
Qiang Duan
EZEnhao Zhan
Enhao Zhan
ZWZizhong Wei
Zizhong Wei
CLChangsheng Liu
Changsheng Liu
RLRui Li
Rui Li
This paper introduces a dataset encompassing images from domains such as pornography, gambling, violence, and drugs. It addresses the gap in harmful image recognition by including data on gambling and drugs, which were previously lacking in this field. This dataset can be utilized to construct and evaluate methods for recognizing harmful images. The paper also proposes a harmful image recognition method based on CLIP model, coupled with strongly and weakly associated prompts, achieving zero-shot learning. The method achieves great accuracy on the dataset presented in the paper, and it incurs low learning costs. These innovations not only underscore the adaptability of the vision-language models but also provide a new paradigm to safeguard children from the potential harms of explicit content, violence, gambling, and drugs in the evolving digital landscape.

26 January 2024
Verified
Conference Paper
Open access
ZWZizhong Wei
Zizhong Wei
RLRui Li
Rui Li
KJKai Jiang
Kai Jiang
QLQingcai Luo
Qingcai Luo
ZSZongchen Sun
Zongchen Sun
YWYang Wang
Yang Wang
With the wide application of Internet of Things, big data and other technologies in smart agriculture, more and more agricultural data are collected and used. The current analysis and processing through IoT platforms and other centralised methods have more serious data security problems. Privacy computing is a technology that completes data security calculations under the premise that both parties do not disclose data, and the data of each participant participates in the calculation is in the form of cipher text to maximally reduce the risk of data leakage. Aiming at the small volume and high frequency scenario of agricultural data, this paper proposes a distributed privacy computing framework by integrating cryptography, edge computing and blockchain, and designs a privacy computing system called PCS-ADS for smart agricultural data. This paper focuses on describing the system model architecture and system function implementation, which includes key business processes, core modules, core algorithms and other parts. Finally, the security and performance evaluation of the system is carried out. The results show that, for sum and variance, the computation time for multi-party under the amount of 1w data of each party is no more than 0.1s, and for the high-frequency computation scenarios, the computation time under the amount of 100 data of each party is no more than 7s and 1.5s, respectively. Experimental results prove that PCS-ADS is effective and has a strong practicality.

24 May 2024
Verified
Conference Paper
Open access
GWGuangxin Wang
Guangxin Wang
XLXue Li
Xue Li
DGDongshen Guo
Dongshen Guo
QDQiang Duan
Qiang Duan
QCQibin Chen
Qibin Chen
ZWZizhong Wei
Zizhong Wei
Identifying and preventing unsafe behaviors is an important task to protect people’s lives and property. Due to the complexity of behavioral types and the fact that many behavioral actions have small amplitude, rendering ineffective spatial and temporal variation information, zero-shot image-based detection of unsafe behaviors is a highly challenging task. The multimodal large language model shows excellent performance in the zero-shot task once it appears. However, it is often impossible to accurately locate and analyze each individual’s behavior in complex scenes solely relying on its ability. Therefore, this paper proposes an innovative zero-shot method to detect unsafe behaviors. We built a two-stage detection model. First, we focus on the target area of people through the target detection algorithm, and then analyze the behavior through the multimodal large language model combined with the construction strategy of positive and negative description prompts. This method shows excellent performance on the dataset we built. It can accurately identify unsafe behaviors in the real environment, which is very important to protect public safety and property.