arXiv subjects

Yiwei Wang

Publications and source records attributed to Yiwei Wang.

At least 181 records · Page 10Linked to original sources

arXiv2024

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts

The knowledge within large language models (LLMs) may become outdated quickly. While in-context editing (ICE) is currently the most effective method for knowledge editing (KE), it is constrained by the black-box modeling of LLMs and thus lacks interpretability. Our work aims to elucidate the superior performance of ICE on the KE by analyzing the impacts of in-context new knowledge on token-wise distributions. We observe that despite a significant boost in logits of the new knowledge, the performance of is still hindered by stubborn knowledge. Stubborn knowledge refers to as facts that have gained excessive confidence during pretraining, making it hard to edit effectively. To address this issue and further enhance the performance of ICE, we propose a novel approach termed $\textbf{De}$coding by $\textbf{C}$ontrasting $\textbf{K}$nowledge (DeCK). DeCK derives the distribution of the next token by contrasting the logits obtained from the newly edited knowledge guided by ICE with those from the unedited parametric knowledge. Our experiments consistently demonstrate that DeCK enhances the confidence of LLMs in edited facts. For instance, it improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%, demonstrating its capability to strengthen ICE in the editing of stubborn knowledge. Our work paves the way to develop the both effective and accountable KE methods for LLMs. (The source code is available at: https://deck-llm.meirtz.com)

cs.CL↗

arXiv2024

Primacy Effect of ChatGPT

Instruction-tuned large language models (LLMs), such as ChatGPT, have led to promising zero-shot performance in discriminative natural language understanding (NLU) tasks. This involves querying the LLM using a prompt containing the question, and the candidate labels to choose from. The question-answering capabilities of ChatGPT arise from its pre-training on large amounts of human-written text, as well as its subsequent fine-tuning on human preferences, which motivates us to ask: Does ChatGPT also inherits humans' cognitive biases? In this paper, we study the primacy effect of ChatGPT: the tendency of selecting the labels at earlier positions as the answer. We have two main findings: i) ChatGPT's decision is sensitive to the order of labels in the prompt; ii) ChatGPT has a clearly higher chance to select the labels at earlier positions as the answer. We hope that our experiments and analyses provide additional insights into building more reliable ChatGPT-based solutions. We release the source code at https://github.com/wangywUST/PrimacyEffectGPT.

cs.CL↗

arXiv2024

How Fragile is Relation Extraction under Entity Replacements?

Relation extraction (RE) aims to extract the relations between entity names from the textual context. In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context. However, existing work has found that the RE models memorize the entity name patterns to make RE predictions while ignoring the textual context. This motivates us to raise the question: ``are RE models robust to the entity replacements?'' In this work, we operate the random and type-constrained entity replacements over the RE instances in TACRED and evaluate the state-of-the-art RE models under the entity replacements. We observe the 30\% - 50\% F1 score drops on the state-of-the-art RE models under entity replacements. These results suggest that we need more efforts to develop effective RE models robust to entity replacements. We release the source code at https://github.com/wangywUST/RobustRE.

cs.CL↗

arXiv2024

Energetic Variational Neural Network Discretizations of Gradient Flows

We present a structure-preserving Eulerian algorithm for solving $L^2$-gradient flows and a structure-preserving Lagrangian algorithm for solving generalized diffusions. Both algorithms employ neural networks as tools for spatial discretization. Unlike most existing methods that construct numerical discretizations based on the strong or weak form of the underlying PDE, the proposed schemes are constructed based on the energy-dissipation law directly. This guarantees the monotonic decay of the system's free energy, which avoids unphysical states of solutions and is crucial for the long-term stability of numerical computations. To address challenges arising from nonlinear neural network discretization, we perform temporal discretizations on these variational systems before spatial discretizations. This approach is computationally memory-efficient when implementing neural network-based algorithms. The proposed neural network-based schemes are mesh-free, allowing us to solve gradient flows in high dimensions. Various numerical experiments are presented to demonstrate the accuracy and energy stability of the proposed numerical schemes.

math.NA↗

arXiv2024

Energetic Variational Gaussian Process Regression for Computer Experiments

The Gaussian process (GP) regression model is a widely employed surrogate modeling technique for computer experiments, offering precise predictions and statistical inference for the computer simulators that generate experimental data. Estimation and inference for GP can be performed in both frequentist and Bayesian frameworks. In this chapter, we construct the GP model through variational inference, particularly employing the recently introduced energetic variational inference method by Wang et al. (2021). Adhering to the GP model assumptions, we derive posterior distributions for its parameters. The energetic variational inference approach bridges the Bayesian sampling and optimization and enables approximation of the posterior distributions and identification of the posterior mode. By incorporating a normal prior on the mean component of the GP model, we also apply shrinkage estimation to the parameters, facilitating mean function variable selection. To showcase the effectiveness of our proposed GP model, we present results from three benchmark examples.

stat.ME↗

arXiv2024

LPNL: Scalable Link Prediction with Large Language Models

Exploring the application of large language models (LLMs) to graph learning is a emerging endeavor. However, the vast amount of information inherent in large graphs poses significant challenges to this process. This work focuses on the link prediction task and introduces $\textbf{LPNL}$ (Link Prediction via Natural Language), a framework based on large language models designed for scalable link prediction on large-scale heterogeneous graphs. We design novel prompts for link prediction that articulate graph details in natural language. We propose a two-stage sampling pipeline to extract crucial information from the graphs, and a divide-and-conquer strategy to control the input tokens within predefined limits, addressing the challenge of overwhelming information. We fine-tune a T5 model based on our self-supervised learning designed for link prediction. Extensive experimental results demonstrate that LPNL outperforms multiple advanced baselines in link prediction tasks on large-scale graphs.

cs.CL↗

arXiv2024

On a positive-preserving, energy-stable numerical scheme to mass-action kinetics with detailed balance

In this paper, we provide a detailed theoretical analysis of the numerical scheme introduced in J. Comput. Phys. 436 (2021) 110253 for the reaction kinetics of a class of chemical reaction networks that satisfies detailed balance condition. In contrast to conventional numerical approximations, which are typically constructed based on ordinary differential equations (ODEs) for the concentrations of all involved species, the scheme is developed using the equations of reaction trajectories, which can be viewed as a generalized gradient flow of physically relevant free energy. The unique solvability, positivity-preserving, and energy-stable properties are proved for the general case involving multiple reactions, under a mild condition on the stoichiometric matrix.

math.NA↗

arXiv2023

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

Road traffic forecasting plays a critical role in smart city initiatives and has experienced significant advancements thanks to the power of deep learning in capturing non-linear patterns of traffic data. However, the promising results achieved on current public datasets may not be applicable to practical scenarios due to limitations within these datasets. First, the limited sizes of them may not reflect the real-world scale of traffic networks. Second, the temporal coverage of these datasets is typically short, posing hurdles in studying long-term patterns and acquiring sufficient samples for training deep models. Third, these datasets often lack adequate metadata for sensors, which compromises the reliability and interpretability of the data. To mitigate these limitations, we introduce the LargeST benchmark dataset. It encompasses a total number of 8,600 sensors in California with a 5-year time coverage and includes comprehensive metadata. Using LargeST, we perform in-depth data analysis to extract data insights, benchmark well-known baselines in terms of their performance and efficiency, and identify challenges as well as opportunities for future research. We release the datasets and baseline implementations at: https://github.com/liuxu77/LargeST.

cs.LG↗

arXiv2023

A Causal View of Entity Bias in (Large) Language Models

Entity bias widely affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired methods have shown great potential to mitigate entity bias, it is hard to precisely estimate the parameters of underlying causal models in practice. The rise of black-box LLMs also makes the situation even worse, because of their inaccessible parameters and uncalibrated logits. To address these problems, we propose a specific structured causal model (SCM) whose parameters are comparatively easier to estimate. Building upon this SCM, we propose causal intervention techniques to mitigate entity bias for both white-box and black-box settings. The proposed causal intervention perturbs the original entity with neighboring entities. This intervention reduces specific biasing information pertaining to the original entity while still preserving sufficient semantic information from similar entities. Under the white-box setting, our training-time intervention improves OOD performance of PLMs on relation extraction (RE) and machine reading comprehension (MRC) by 5.7 points and by 9.1 points, respectively. Under the black-box setting, our in-context intervention effectively reduces the entity-based knowledge conflicts of GPT-3.5, achieving up to 20.5 points of improvement of exact match accuracy on MRC and up to 17.6 points of reduction in memorization ratio on RE. Our code is available at https://github.com/luka-group/Causal-View-of-Entity-Bias.

cs.CL↗

arXiv2023

Two-dimensional Ferronematics, Canonical Harmonic Maps and Minimal Connections

We study a variational model for ferronematics in two-dimensional domains, in the "super-dilute" regime. The free energy functional consists of a reduced Landau-de Gennes energy for the nematic order parameter, a Ginzburg-Landau type energy for the spontaneous magnetisation, and a coupling term that favours the co-alignment of the nematic director and the magnetisation. In a suitable asymptotic regime, we prove that the nematic order parameter converges to a canonical harmonic map with non-orientable point defects, while the magnetisation converges to a singular vector field, with line defects that connect the non-orientable point defects in pairs, along a minimal connection.

math.AP↗

arXiv2023

RECIPE: Rateless Erasure Codes Induced by Protocol-Based Encoding

LT (Luby transform) codes are a celebrated family of rateless erasure codes (RECs). Most of existing LT codes were designed for applications in which a centralized encoder possesses all message blocks and is solely responsible for encoding them into codewords. Distributed LT codes, in which message blocks are physically scattered across multiple different locations (encoders) that need to collaboratively perform the encoding, has never been systemically studied before despite its growing importance in applications. In this work, we present the first systemic study of LT codes in the distributed setting, and make the following three major contributions. First, we show that only a proper subset of LT codes are feasible in the distributed setting, and give the sufficient and necessary condition for such feasibility. Second, we propose a distributed encoding protocol that can efficiently implement any feasible code. The protocol is parameterized by a so-called action probability array (APA) that is only a few KBs in size, and any feasible code corresponds to a valid APA setting and vice versa. Third, we propose two heuristic search algorithms that have led to the discovery of feasible codes that are much more efficient than the state of the art.

cs.IT↗

arXiv2023

High energy beam energy measurement with microwave-electron Compton backscattering

The uncertainty of the energy measurement of the electron beam on circular electron positron collider (CEPC) must be smaller than 10$\mathrm{MeV}$ to make sure the accurate measurement of the mass of the Higgs boson. In order to simplify the energy measurement system, a new method is proposed by fitting the Compton edge of the energy distribution of the gamma ray from a microwave-electron Compton scattering. With our method, the uncertainty of the energy measurement is 6$\mathrm{MeV}$ for the electron energy of $120\mathrm{GeV}$ in the Higgs mode. In this system, the energy resolution of the gamma detection needs to reach $10^{-4}$. Therefore, only the high-purity germanium (HPGe) detector can meet the critical requirement. In a head-on collision mode, the initial photons should be microwave photons with the wavelength of 3.04 centimeters. A cylindrical resonant cavity with selected ${TM_{010}}$ mode is used to transmit microwaves. After the microwave-electron Compton backscattering, the scattered photons and the synchrotron-radiation background transmit a shielding structure and then are detected by a HPGe detector at the end of the beam line of the synchrotron-radiation applications. The hole radius in the side wall of the cavity is about $1.5\mathrm{mm}$ to allow the electron beam passing through. The results of the computer simulation technology (CST) software shows that the influence of the hole radius on the cavity field is negligible. The change of the resonance frequency can be easily corrected by fine-tuning the cavity size.

hep-ex↗

arXiv2023

Evaluation of radiative depolarization in the future Circular Electron-Positron Collider

Polarized lepton beams are an important aspect in the design of the future 100 km-scale Circular Electron-Positron Collider (CEPC). Precision beam energy calibration using resonant depolarization, as well as longitudinally polarized colliding beams are being actively investigated. The achievable beam polarization level for various beam energies and application scenarios depends on the radiative depolarization in the collider rings. In this paper the radiative depolarization effects are evaluated for a CEPC collider ring lattice with detailed machine imperfections and corrections. Simulations with the SLIM and Monte-Carlo approaches using the Bmad/PTC codes are compared with the theory of the effects of spin diffusion for ultra-high beam energies and the validity of the theories is thereby addressed. The paper concludes with a summary and suggestions for further investigations.

physics.acc-ph↗

arXiv2022

Flashlight: Scalable Link Prediction with Effective Decoders

Link prediction (LP) has been recognized as an important task in graph learning with its broad practical applications. A typical application of LP is to retrieve the top scoring neighbors for a given source node, such as the friend recommendation. These services desire the high inference scalability to find the top scoring neighbors from many candidate nodes at low latencies. There are two popular decoders that the recent LP models mainly use to compute the edge scores from node embeddings: the HadamardMLP and Dot Product decoders. After theoretical and empirical analysis, we find that the HadamardMLP decoders are generally more effective for LP. However, HadamardMLP lacks the scalability for retrieving top scoring neighbors on large graphs, since to the best of our knowledge, there does not exist an algorithm to retrieve the top scoring neighbors for HadamardMLP decoders in sublinear complexity. To make HadamardMLP scalable, we propose the Flashlight algorithm to accelerate the top scoring neighbor retrievals for HadamardMLP: a sublinear algorithm that progressively applies approximate maximum inner product search (MIPS) techniques with adaptively adjusted query embeddings. Empirical results show that Flashlight improves the inference speed of LP by more than 100 times on the large OGBL-CITATION2 dataset without sacrificing effectiveness. Our work paves the way for large-scale LP applications with the effective HadamardMLP decoders by greatly accelerating their inference.

cs.SI↗

arXiv2022

AirFormer: Predicting Nationwide Air Quality in China with Transformers

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic and social growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries like China. In this paper, we present a novel Transformer architecture termed AirFormer to collectively predict nationwide air quality in China, with an unprecedented fine spatial granularity covering thousands of locations. AirFormer decouples the learning process into two stages -- 1) a bottom-up deterministic stage that contains two new types of self-attention mechanisms to efficiently learn spatio-temporal representations; 2) a top-down stochastic stage with latent variables to capture the intrinsic uncertainty of air quality data. We evaluate AirFormer with 4-year data from 1,085 stations in the Chinese Mainland. Compared to the state-of-the-art model, AirFormer reduces prediction errors by 5%~8% on 72-hour future predictions. Our source code is available at https://github.com/yoshall/airformer.

eess.SP↗

arXiv2022

Top quark mass measurements at the $t\bar{t}$ threshold with CEPC

We present a study of top quark mass measurements at the $t\bar{t}$ threshold based on CEPC. A centre-of-mass energy scan near two times of the top mass is performed and the measurement precision of top quark mass, width and $α_S$ are evaluated using the $t\bar{t}$ production rates. Realistic scan strategies at the threshold are discussed to maximise the sensitivity to the measurement of the top quark properties individually and simultaneously in the CEPC scenarios assuming a limited total luminosity of 100 fb$^{-1}$. With the optimal scan for individual property measurements, the top quark mass precision is expected to be 9 MeV, the top quark width precision is expected to be 26 MeV, and $α_S$ can be measured at a precision of 0.00039. Taking into account the uncertainties from theory, background subtraction, beam energy and luminosity spectrum, the top quark mass can be measured at a precision of 14 MeV optimistically and 34 MeV conservatively at CEPC.

hep-ex↗

arXiv2022

LSCALE: Latent Space Clustering-Based Active Learning for Node Classification

Node classification on graphs is an important task in many practical domains. It usually requires labels for training, which can be difficult or expensive to obtain in practice. Given a budget for labelling, active learning aims to improve performance by carefully choosing which nodes to label. Previous graph active learning methods learn representations using labelled nodes and select some unlabelled nodes for label acquisition. However, they do not fully utilize the representation power present in unlabelled nodes. We argue that the representation power in unlabelled nodes can be useful for active learning and for further improving performance of active learning for node classification. In this paper, we propose a latent space clustering-based active learning framework for node classification (LSCALE), where we fully utilize the representation power in both labelled and unlabelled nodes. Specifically, to select nodes for labelling, our framework uses the K-Medoids clustering algorithm on a latent space based on a dynamic combination of both unsupervised features and supervised features. In addition, we design an incremental clustering module to avoid redundancy between nodes selected at different steps. Extensive experiments on five datasets show that our proposed framework LSCALE consistently and significantly outperforms the stateof-the-art approaches by a large margin.

cs.LG↗

arXiv2022

Investigation of spin rotators in CEPC at the Z-pole

Longitudinal polarization is an important design aspect of the future 100 km-scale Circular Electron Position Collider (CEPC). Spin rotators are needed in CEPC collider rings to make the beam polarization along the longitudinal direction at the interaction points (IPs). This paper focuses on the design of spin rotators for CEPC at Z-pole (45.6 GeV). The design of spin rotators in CEPC at Z-pole is based on solenoid magnets and horizontal bending magnets sections. The coupling of transverse motion introduced by solenoids is compensated with quadrupole lenses. Adjustments have been made to the layout to implement the spin rotators into the collider rings.Longitudinal polarized beam can be achieved at the IPs with the spin rotators. High degree of polarization is attainable, while the effect of spin rotators on orbital motion is acceptable. The detailed simulation results will be presented.A solenoid-based spin rotator configuration is designed and integrated into the CEPC collider ring lattice. According to the simulation results, the polarization requirements can be satisfied.

physics.acc-ph↗