arXiv subjects

Qili Zhang

Publications and source records attributed to Qili Zhang.

8 recordsLinked to original sources

arXiv2026

Selective Knowledge Edit Reversal via Gated Singular Vector Shrinkage

Knowledge editing provides an efficient way to update factual knowledge in large language models. However, malicious edits may introduce safety risks, making it necessary to reverse undesirable editing effects. Existing reversal methods for parameter-modifying edits mainly focus on global removal, which may also erase beneficial edits that should be preserved. In this paper, we study selective reversal of edited knowledge, where the goal is to reverse targeted edited facts while preserving the remaining edited facts. Based on the hypothesis that each edit is sparsely encoded within the dominant subspace of the edited matrix, we propose a spectral-based reversal framework that locates edit-sensitive components within the dominant singular subspace of edited weights. Experiments across multiple settings demonstrate the effectiveness of our method in reversing selected edits while preserving unrelated edited facts. These results suggest that different edits are sparsely encoded within dominant singular components and can be separable when the number of edits is moderate, making selective spectral reversal a promising direction for locating edit-specific components and repairing edited language models.

cs.CL↗

arXiv2026

NanoNet: Parameter-Efficient Learning with Label-Scarce Supervision for Lightweight Text Mining Model

The lightweight semi-supervised learning (LSL) strategy provides an effective approach of conserving labeled samples and minimizing model inference costs. Prior research has effectively applied knowledge transfer learning and co-training regularization from large to small models in LSL. However, such training strategies are computationally intensive and prone to local optima, thereby increasing the difficulty of finding the optimal solution. This has prompted us to investigate the feasibility of integrating three low-cost scenarios for text mining tasks: limited labeled supervision, lightweight fine-tuning, and rapid-inference small models. We propose NanoNet, a novel framework for lightweight text mining that implements parameter-efficient learning with limited supervision. It employs online knowledge distillation to generate multiple small models and enhances their performance through mutual learning regularization. The entire process leverages parameter-efficient learning, reducing training costs and minimizing supervision requirements, ultimately yielding a lightweight model for downstream inference.

cs.LG↗

arXiv2025

Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has recently emerged as a promising solution for enhancing the accuracy and credibility of Large Language Models (LLMs), particularly in Question & Answer tasks. This is achieved by incorporating proprietary and private data from integrated databases. However, private RAG systems face significant challenges due to the scarcity of private domain data and critical data privacy issues. These obstacles impede the deployment of private RAG systems, as developing privacy-preserving RAG systems requires a delicate balance between data security and data availability. To address these challenges, we regard federated learning (FL) as a highly promising technology for privacy-preserving RAG services. We propose a novel framework called Federated Retrieval-Augmented Generation (FedE4RAG). This framework facilitates collaborative training of client-side RAG retrieval models. The parameters of these models are aggregated and distributed on a central-server, ensuring data privacy without direct sharing of raw data. In FedE4RAG, knowledge distillation is employed for communication between the server and client models. This technique improves the generalization of local RAG retrievers during the federated learning process. Additionally, we apply homomorphic encryption within federated learning to safeguard model parameters and mitigate concerns related to data leakage. Extensive experiments conducted on the real-world dataset have validated the effectiveness of FedE4RAG. The results demonstrate that our proposed framework can markedly enhance the performance of private RAG systems while maintaining robust data privacy protection.

cs.CL↗

arXiv2025

The chemisorption thermodynamics of O$_2$ and H$_2$O on AFM UO$_2$ surfaces unraveled by DFT+U-D3 study

Unraveling the adsorption mechanism and thermodynamics of O$_2$ and H$_2$O on uranium dioxide surfaces is critical for the nuclear fuel storage and uranium corrosion. Based on the first-principles DFT+U-D3 calculations, we carefully test the effect of antiferromagnetic order arrangements on the thermodynamic stability of UO$_2$ surfaces and propose the 1k AFM surface computational model. The chemisorption states of O$_2$ and H$_2$O on UO$_2$ (111) surface, suggested by previous experiments, are accurately calculated for the first time. The adsorption properties of O$_2$ and H$_2$O on UO$_2$(111) and (110) surfaces are discussed in detail to reveal the different interaction mechanisms. Combined with ab initio atomistic thermodynamics method, we systematically calculate the chemisorption phase diagram and isotherm of O$_2$ and H$_2$O on UO$_2$ surfaces. Due to the different intermolecular interactions, the monolayer and multilayer adsorption models are identified for O$_2$ and H$_2$O, respectively. This study has comprehensively revealed the different adsorption mechanisms of O$_2$ and H$_2$O on UO$_2$ surfaces, bridging the electronic structure calculations to the interpretation of experimental results and providing a solid foundation for future theoretical studies of uranium corrosion mechanism in humid air.

cond-mat.mtrl-sci↗

arXiv2024

XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) synergizes the retrieval of pertinent data with the generative capabilities of Large Language Models (LLMs), ensuring that the generated output is not only contextually relevant but also accurate and current. We introduce XRAG, an open-source, modular codebase that facilitates exhaustive evaluation of the performance of foundational components of advanced RAG modules. These components are systematically categorized into four core phases: pre-retrieval, retrieval, post-retrieval, and generation. We systematically analyse them across reconfigured datasets, providing a comprehensive benchmark for their effectiveness. As the complexity of RAG systems continues to escalate, we underscore the critical need to identify potential failure points in RAG systems. We formulate a suite of experimental methodologies and diagnostic testing protocols to dissect the failure points inherent in RAG engineering. Subsequently, we proffer bespoke solutions aimed at bolstering the overall performance of these modules. Our work thoroughly evaluates the performance of advanced core components in RAG systems, providing insights into optimizations for prevalent failure points.

cs.CL↗

arXiv2020

First-Principles Study of Hydrogen Behaviors in $α$-Pu$_{2}$O$_{3}$

The in-depth understanding of hydrogen permeation through plutonium-oxide overlayers is the prerequisite to evaluate the complex hydriding induction period of Pu. In this work, the incorporation, diffusion and dissolution of hydrogen in $α$-Pu$_{2}$O$_{3}$ are investigated by the first-principles calculations and $\textit{ab initio}$ thermodynamic method based on DFT+U and DFT-D3 schemes. Our study reveals that the hydrogen incorporation is endothermic and the separated H atoms prefer to recombine as H$_{2}$ molecules rather than reacting with $α$-Pu$_{2}$O$_{3}$. The H and H$_{2}$ diffusion are both feasible, generally, H will recombine first as H$_{2}$ and then migrate. Both pressure P$_{H2}$ and temperature can promote the hydrogen dissolution in $α$-Pu$_{2}$O$_{3}$. The single H$_{2}$ molecule incorporation and (H+H$_{2}$) mixed dissolution will successively appear when increasing P$_{H2}$. Compared to PuO$_{2}$, this work indicates that Pu sesquioxide is hardly reduced by hydrogen, but the porous $α$-Pu$_{2}$O$_{3}$ facilitates hydrogen transport in Pu oxide layers. We presents the microscopic picture of hydrogen behaviors in the defect-free $α$-Pu$_{2}$O$_{3}$, which could shed some light on the study of the hydriding induction period of Pu.

cond-mat.mtrl-sci↗

arXiv2007

Equation of state for shock-compressed porous molybdenum from first-principles mean-field potential calculations

The Hugoniot curves for shock-compressed molybdenum with initial porosities of 1.0, 1.26, 1.83, and 2.31 are theoretically investigated. The method of calculations combines the first-principles treatment for zero- and finite-temperature electronic contribution and the mean-field-potential approach for the ion-thermal contribution to the total free energy. Our calculated results reproduce the Hugoniot properties of porous molybdenum quite well. At low porosity, in particular, the calculations show a complete agreement with the experimental measurements over the full range of data. For the two large porosity values of 1.83 and 2.31, our results are well in accord with the experimental data points up to the particle velocity of 3.5 km/s, and tend to overestimate the shock-wave velocity and Hugoniot pressure when further increasing the particle velocity. In addition, the temperature along the principal Hugoniot is also extensively investigated for porous molybdenum.

cond-mat.mtrl-sci↗

arXiv2007

Mean-field potential calculations of high-pressure equation of state for shock-compressed BeO

A systematic study of the Hugoniot equation of state, phase transition, and the other thermodynamic properties including the Hugoniot temperature, the electronic and ionic heat capacities, and the Grüneisen parameter for shock-compressed BeO, is presented by calculating the total free energy. The method of calculations combines first-principles treatment for 0-K and finite-T electronic contribution and the mean-field-potential approach for the vibrational contribution of the lattice ion to the total energy. Our calculated Hugoniot shows good agreement with the experimental data.

cond-mat.mtrl-sci↗