Author name cluster

Jie Meng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

ICML Conference 2024 Conference Paper

Position: Building Guardrails for Large Language Models Requires Systematic Design

Yi Dong 0002
Ronghui Mu
Gaojie Jin
Yi Qi
Jinwei Hu
Xingyu Zhao 0001
Jie Meng
Wenjie Ruan

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the inputs or outputs of LLMs, have emerged as a core safeguarding technology. This position paper takes a deep look at current open-source solutions (Llama Guard, Nvidia NeMo, Guardrails AI), and discusses the challenges and the road towards building more complete solutions. Drawing on robust evidence from previous research, we advocate for a systematic approach to construct guardrails for LLMs, based on comprehensive consideration of diverse contexts across various LLMs applications. We propose employing socio-technical methods through collaboration with a multi-disciplinary team to pinpoint precise technical requirements, exploring advanced neural-symbolic implementations to embrace the complexity of the requirements, and developing verification and testing to ensure the utmost quality of the final product.

Details

YNIMG Journal 2021 Journal Article

Connectome-based evidence for creative thinking as an emergent property of ordinary cognitive operations

Kaixiang Zhuang
Wenjing Yang
Yu Li
Jie Zhang
Qunlin Chen
Jie Meng
Dongtao Wei
Jiangzhou Sun

Creative thinking is a hallmark of human cognition, which enables us to generate novel and useful ideas. Nevertheless, its emergence within the macro-scale neurocognitive circuitry remains largely unknown. Using resting-state fMRI data from two large population samples (SWU: n = 931; HCP: n = 1001) and a novel "travelling pattern prediction analysis", here we identified the modularized functional connectivity patterns linked to creative thinking ability, which concurrently explained individual variability across ordinary cognitive abilities such as episodic memory, working memory and relational processing. Further interrogation of this neural pattern with graph theoretical tools revealed both hub-like brain structures and globally-efficient information transfer paths that together may facilitate higher creative thinking ability through the convergence of distinct cognitive operations. Collectively, our results provide reliable evidence for the hypothesized emergence of creative thinking from core cognitive components through neural integration, and thus allude to a significant theoretical advancement in the study of creativity.

Details DOI

YNIMG Journal 2019 Journal Article

Reproducibility of functional brain alterations in major depressive disorder: Evidence from a multisite resting-state functional MRI study with 1,434 individuals

Mingrui Xia
Tianmei Si
Xiaoyi Sun
Qing Ma
Bangshan Liu
Li Wang
Jie Meng
Miao Chang

Resting-state functional MRI (R-fMRI) studies have demonstrated widespread alterations in brain function in patients with major depressive disorder (MDD). However, a clear and consistent conclusion regarding a repeatable pattern of MDD-relevant alterations is still limited due to the scarcity of large-sample, multisite datasets. Here, we address this issue by including a large R-fMRI dataset with 1434 participants (709 patients with MDD and 725 healthy controls) from five centers in China. Individual functional activity maps that represent very local to long-range connections are computed using the amplitude of low-frequency fluctuations, regional homogeneity and distance-related functional connectivity strength. The reproducibility analyses involve different statistical strategies, global signal regression, across-center consistency, clinical variables, and sample size. We observed significant hypoactivity in the orbitofrontal, sensorimotor, and visual cortices and hyperactivity in the frontoparietal cortices in MDD patients compared to the controls. These alterations are not affected by different statistical analysis strategies, global signal regression and medication status and are generally reproducible across centers. However, these between-group differences are partially influenced by the episode status and the age of disease onset in patients, and the brain-clinical variable relationship exhibits poor cross-center reproducibility. Bootstrap analyses reveal that at least 400 subjects in each group are required to replicate significant alterations (an extent threshold of P <. 05 and a height threshold of P <. 001) at 50% reproducibility. Together, these results highlight reproducible patterns of functional alterations in MDD and relevant influencing factors, which provides crucial guidance for future neuroimaging studies of this disorder.

Details DOI

YNIMG Journal 2016 Journal Article

Assessment of trait anxiety and prediction of changes in state anxiety using functional brain imaging: A test–retest study

Xue Tian
Dongtao Wei
Xue Du
Kangcheng Wang
Junyi Yang
Wei Liu
Jie Meng
Huijuan Liu

Anxiety is a multidimensional construct that includes stable trait anxiety and momentary state anxiety, which have a combined effect on our mental and physical well-being. However, the relationship between intrinsic brain activity and the feeling of anxiety, particularly trait and state anxiety, remain unclear. In this study, we used resting-state functional magnetic resonance imaging (fMRI) (amplitude of low-frequency fluctuations (ALFF) and regional homogeneity (ReHo)) to determine the effects of intrinsic brain activity on stable inter-individual trait anxiety and intra-individual state anxiety variability in a cross-sectional and test–retest study. We found that at both time points, the trait anxiety score was significantly associated with intrinsic brain activity (both the ALFF and ReHo) in the right ventral medial prefrontal cortex (vmPFC) and ALFF of the dorsal anterior cingulate cortex/anterior midcingulate cortex (dACC/aMCC). More importantly, the change in intrinsic brain activity in the right insula was predictive of intra-individual state anxiety variability over a 9-month interval. The test–retest nature of this study's design could provide an opportunity to distinguish between the intrinsic brain activity associated with state and trait anxiety. These results could deepen our understanding of anxiety from a neuroscientific perspective.

Details DOI

IJCAI Conference 2016 Conference Paper

Reconfigurability in Reactive Multiagent Systems

Xiaowei Huang
Qingliang Chen
Jie Meng
Kaile Su

Reactive agents are suitable for representing physical resources in manufacturing control systems. An important challenge of agent-based manufacturing control systems is to develop formal and structured approaches to support their specification and verification. This paper proposes a logic-based approach, by generalising that of model checking multiagent systems, for the reconfigurability of reactive multiagent systems. Two reconfigurability scenarios are studied, for the resulting system being a monolithic system or an individual module, and their computational complexity results are given.

PDF Details

TCS Journal 2013 Journal Article

Parameterized top- K algorithms

Jianer Chen
Iyad A. Kanj
Jie Meng
Ge Xia
Fenghui Zhang

We study algorithmic techniques that produce the best K solutions to an instance of a parameterized NP-hard problem whose solutions are associated with a scoring function. Our parameterized top- K algorithms proceed in two stages. The first stage is a structure algorithm that on a problem instance constructs a structure of feasible size, and the second stage is an enumerating algorithm that produces the K best solutions to the instance based on the structure. We show that many algorithm-design techniques for parameterized algorithms, such as branch-and-search, color coding, and bounded treewidth, can be adopted for designing efficient structure algorithms. We then develop new techniques that support efficient enumerating algorithms. In particular, we show that for a large class of well-known NP optimization problems, there are parameterized top- K algorithms that produce the best K solutions for the problems in feasible amount of average time per solution when the parameter value is small. Finally, we investigate the relation between fixed-parameter tractability and parameterized top- K algorithms.

Details DOI

TCS Journal 2009 Journal Article

On the pseudo-achromatic number problem

Jianer Chen
Iyad A. Kanj
Jie Meng
Ge Xia
Fenghui Zhang

We study the parameterized complexity of the pseudo-achromatic number problem: Given an undirected graph and a parameter k, determine if the graph can be partitioned into k groups such that every two groups are connected by at least one edge. This problem has been extensively studied in graph theory and combinatorial optimization. We show that the problem has a kernel of at most ( k − 2 ) ( k + 1 ) vertices that is constructable in time O ( m n ), where n and m are the number of vertices and edges, respectively, in the graph, and k is the parameter. This directly implies that the problem is fixed-parameter tractable. We also study generalizations of the problem and show that they are parameterized intractable.

Details DOI