Jichen Zhang

Mr. Jichen Zhang

orcid

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
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 May 2023 in Journal of Applied Probability
Verified
Journal Article
Closed access
PDF file
ZCZengjing Chen
Zengjing Chen
YLYiwei Lin
Yiwei Lin
JZJichen Zhang
Jichen Zhang
The myopic strategy is one of the most important strategies when studying bandit problems. In 2018, Nouiehed and Ross put forward a conjecture about Feldman’s bandit problem (J. Appl. Prob. (2018) 55, 318–324). They proposed that for Bernoulli two-armed bandit problems, the myopic strategy stochastically maximizes the number of wins. In this paper we consider the two-armed bandit problem with more general distributions and utility functions. We confirm this conjecture by proving a stronger result: if the agent playing the bandit has a general utility function, the myopic strategy is still optimal if and only if this utility function satisfies reasonable conditions.

12 February 2026
Verified
Book Chapter
Closed access
LZLei Zhang
Lei Zhang
XZXianglong Zhou
Xianglong Zhou
EZEnhao Zhan
Enhao Zhan
HZHaozhi Zhang
Haozhi Zhang
QDQiang Duan
Qiang Duan
JZJichen Zhang
Jichen Zhang


1 February 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
JZJichen Zhang
Jichen Zhang
PWPanyu Wu
Panyu Wu
In this paper, we study an independent Bernoulli two-armed bandit with unknown parameters ρ and λ, where ρ and λ have a pair of priori distributions such that dR(ρ)=CRρr0(1−ρ)r0′dμ(ρ),dL(λ)=CLλl0(1−λ)l0′dμ(λ) and μ is an arbitrary positive measure on [0,1]. Berry proposed the conjecture that, given a pair of priori distributions (R,L) of parameters ρ and λ, the arm with R is the current optimal choice if r0+r0′<l0+l0′ and the expectation of ρ is not less than that of λ. We give an easily verifiable equivalent form of Berry’s conjecture and use it to prove that Berry’s conjecture holds when R and L are two-point distributions as well as when R and L are beta distributions and the number of trials N≤r0r0′+1.