arXiv subjects

Qianli Zhou

Publications and source records attributed to Qianli Zhou.

16 recordsLinked to original sources

arXiv2026

Quantum Information Fusion and Correction under the Transferable Belief Model

The transferable belief model (TBM), developed within Dempster-Shafer theory, represents ambiguity and partial ignorance through set-valued belief masses. Its classical operations, however, can grow combinatorially over the power set. We formulate TBM reasoning on quantum circuits using the mass function quantum state (MFQS). The resulting framework covers belief representation, credal-level fusion and correction, product-space operations, and the generalized Bayesian theorem. For prepared MFQS inputs, CCR and the entire $α$-junction use element-wise gate modules whose logical counts are linear in the number of frame elements. These circuits avoid explicit operation-stage updates over all $2^n$ focal-set coordinates. A noisy multi-domain classifier-fusion example further demonstrates interpretable source fusion and improved robustness to gate-control noise. The results establish Dempster-Shafer structures as a semantic layer for quantum information processing beyond singleton-probability representations.

cs.AI↗

arXiv2026

Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention

Large language models (LLMs) demonstrate powerful capabilities across various natural language processing tasks,yet their inherent safety vulnerabilities undermine the reliable application of LLMs in real-world scenarios. To enhance LLM safety, various jailbreak defense methods have been proposed to guard against harmful outputs. However, improvements in model safety often come at the cost of severe over-refusal, failing to strike a good balance between safety and usability. This phenomenon is a critical reliability degradation issue in LLM intelligent systems, failing to strike a good balance between safety defense effectiveness and system usability reliability. In this paper, we first analyze the causes of over-refusal from a representation perspective, revealing that LLMs are unable to effectively distinguish between over-refusal samples and malicious samples. Based on this, we propose to mitigate overrefusal by intervening in the safety representation space of LLMs. Our method incorporates two core strategies: (1) OverlapAware Loss Weighting, which determines the erasure weight for malicious samples by quantifying their similarity to overrefusal samples in the representation space, and (2) ContextAware Augmentation, which supplements the necessary context for rejection decisions by adding harmful prefixes before rejection responses. Experiments demonstrate that our method achieves a better trade-off between mitigating over-refusal and maintaining safety, compared with existing approaches. This paper also aims to encourage researchers to consider the reliability of defending methods against jailbreak attacks from both the perspectives of safety and over-refusal.

cs.CR↗

arXiv2026

Quantum Incremental Learning with Mixed State Prototypes

Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints. In the Noisy Intermediate-Scale Quantum (NISQ) era, although quantum neural networks offer advantages in feature mapping, hardware limitations restrict circuit width. Furthermore, traditional quantum classifiers are constrained by the number of orthogonal basis states, limiting their capacity to accommodate a continually growing number of categories. Thus, we introduce a novel quantum incremental learning framework based on trainable mixed-state prototypes. Its original design incorporates new classes by adding class prototypes rather than increasing the circuit width of the shared quantum backbone. The use of mixed-state prototypes is another key contribution, since they have representation capabilities to represent information than a single pure-state prototype. And the decomposable mixed-state calculation provides lower production costs and a convenient Hilbert-Schmidt (HS) distance metric for classification. Simulation results show that our model achieves high-dimensional feature concentration using a minimal number of qubits, while demonstrating lower computational complexity and robust representation in incremental learning tasks compared with classical baselines.

cs.AI↗

arXiv2026

DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning

Task-specific fine-tuning can improve the performance of large language models (LLMs) on downstream tasks. However, our study reveals that task-specific fine-tuning can also weaken the safety guardrails of aligned LLMs. A widely adopted strategy for preserving safety during fine-tuning is to incorporate safety data. Although previous studies have shown that randomly mixing safety data can alleviate safety degradation, the underlying principle determining why some safety examples are more effective than others still remains unclear. In this paper, we propose DataRx, a missingness-aware sampling method for selecting safety-critical examples. DataRx is based on the hypothesis that a safety sample is more effective when the selected examples provide safety signals that fill the missing parts of LLMs' safety capabilities. DataRx's key insight is leveraging high-dimensional hidden representations rather than discrete tokens to quantify the safety signal gap between the target model's native response and the safety reference response. The results show that, with only 1% additional safety samples from BeaverTails, DataRx reduces the average attack success rate of Llama3-8B-Instruct across seven downstream tasks from 59.23% under random sampling to 13.70%. In addition, DataRx can be combined with the existing safety data synthesis method to further enhance safety defenses during fine-tuning. We hope that DataRx will inspire more data-centric defense research.

cs.CL↗

arXiv2026

DOW-KE: Anchor-Free Multi-Layer Knowledge Editing via Direct End-to-End Weight Optimization

Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer as weight updates. This pipeline optimizes an intermediate representation but deploys multi-layer weight updates whose joint effect through the true forward pass is never itself optimized: regardless of how anchors are set or propagated, each update comes from a local solve, so propagation-induced attenuation and distortion go uncorrected, leaving a closure gap between anchor targets and realized edits. We propose DOW-KE, an anchor-free method built on a single principle: what is optimized must be exactly what is deployed. DOW-KE backpropagates the final editing objective through the complete model, jointly optimizing the updates of all edited layers so cross-layer propagation and coupling enter every gradient step. The same principle dictates where preservation resides: embedding the preservation projection in the update parameterization, inside the computation graph, makes every gradient act on the deployed update; post-hoc constraints would reopen the gap, and the constrained search keeps edits clear of protected knowledge. In large-scale sequential editing on two datasets and three models, DOW-KE achieves the highest overall Score and neighborhood Specificity in five of six model-dataset settings among the evaluated baselines.

cs.LG↗

arXiv2026

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning

Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets. However, existing methods for identifying safety-degrading samples in benign datasets suffer from high computational costs and significant noise issues. In this paper, we propose DataShield to efficiently and effectively identify potential safety-degrading samples. Our key intuition is based on the observation that benign fine-tuning increases the overall response compliance of LLMs. DataShield's key technical insight is to quantify each sample's contribution to the model's compliance behavior as its safety degradation score. DataShield consists of three core components: (1) Compliance Vector Extraction, which captures the LLM's compliance behavior tendency; (2) a novel Compliance-Aware Score (CAS), which automatically identifies the optimal safety-critical layer; and (3) Safety-degrading Sample Filtering, which quantifies the projection shift of training data along the compliance direction. Extensive experimental evaluation on Llama3-8B, Llama3.1-8B, and Qwen2.5-7B using the Alpaca and Dolly benign datasets validates our method's effectiveness in identifying high-risk and low-risk data subsets. We also observe that open-ended question answering is more likely to trigger safety degradation, and corresponding responses tend to be longer. We hope this work can provide new insights into data-centric defense methods. The source code is available at: https://github.com/ZJunBo/DataShield.

cs.CR↗

arXiv2026

Evidential Information Fusion on Possibilistic Structure

Dempster's rule is a fundamental tool for combining belief functions from distinct and reliable sources. However, its intersection-based semantics imposes strong structural restrictions, which limits its flexibility in handling complex source states and diverse information fusion scenarios. To overcome this limitation, we propose a reversible transformation, derived from the isopignistic principle, between belief functions and a possibilistic structure defined on the power set. In this transformation, the relationships among subsets are explicitly characterized by a belief evolution network, which provides a more flexible representation of evidential information beyond the conventional mass function structure. On this basis, we further introduce the triangular norm family to develop a general and adaptive evidential information fusion framework. Unlike fusion methods rooted in Dempster semantics, the proposed framework supports more flexible combination behaviors and exhibits advantages in non-distinct source fusion, conflict management, parametric combination design, and heterogeneous information fusion.

cs.AI↗

arXiv2026

Evidential Quantum Vertical Federated Learning

Quantum federated learning (QFL) has recently emerged as a promising paradigm for privacy-preserving collaborative learning, yet most existing studies focus on horizontal federated learning and ignore the vertical federated learning (VFL), where parties hold complementary features of aligned samples. In this work, we propose Evidential Quantum Vertical Federated Learning (eviQVFL), a VFL-tailored QFL framework that employs a hybrid classical-quantum architecture for party-side feature processing, mapping local features into a quantum state. To preserve privacy and avoid information loss, party-side output states are directly transmitted to the server via quantum teleportation, and the server fuses the received quantum states with a non-parametric evidential fusion circuit grounded in evidence theory, followed by measurement-based inference. Extensive simulations on image classification and other real-world datasets demonstrate that eviQVFL consistently achieves higher classification accuracy than other classical and quantum baselines under comparable parameter budgets. Both empirical observations and theoretical analysis indicate that eviQVFL achieve less approximation error with limited quantum resources, while maintaining training stability and offering stronger feature privacy.

quant-ph↗

arXiv2026

Feature Entanglement-based Quantum Multimodal Fusion Neural Network

Multimodal learning aims to enhance perceptual and decision-making capabilities by integrating information from diverse sources. However, classical deep learning approaches face a critical trade-off between the high accuracy of black-box feature-level fusion and the interpretability of less outstanding decision-level fusion, alongside the challenges of parameter explosion and complexity. This paper discusses the accuracy-interpretablity-complexity dilemma under the quantum computation framework and propose a feature entanglement-based quantum multimodal fusion neural network. The model is composed of three core components: a classical feed-forward module for unimodal processing, an interpretable quantum fusion block, and a quantum convolutional neural network (QCNN) for deep feature extraction. By leveraging the strong expressive power of quantum, we have reduced the complexity of multimodal fusion and post-processing to linear, and the fusion process also possesses the interpretability of decision-level fusion. The simulation results demonstrate that our model achieves classification accuracy comparable to classical networks with dozens of times of parameters, exhibiting notable stability and performance across multimodal image datasets.

quant-ph↗

arXiv2025

Attribute Fusion-based Classifier on Framework of Belief Structure

Dempster-Shafer Theory (DST) provides a powerful framework for modeling uncertainty and has been widely applied to multi-attribute classification tasks. However, traditional DST-based attribute fusion-based classifiers suffer from oversimplified membership function modeling and limited exploitation of the belief structure brought by basic probability assignment (BPA), reducing their effectiveness in complex real-world scenarios. This paper presents an enhanced attribute fusion-based classifier that addresses these limitations through two key innovations. First, we adopt a selective modeling strategy that utilizes both single Gaussian and Gaussian Mixture Models (GMMs) for membership function construction, with model selection guided by cross-validation and a tailored evaluation metric. Second, we introduce a novel method to transform the possibility distribution into a BPA by combining simple BPAs derived from normalized possibility distributions, enabling a much richer and more flexible representation of uncertain information. Furthermore, we apply the belief structure-based BPA generation method to the evidential K-Nearest Neighbors (EKNN) classifier, enhancing its ability to incorporate uncertainty information into decision-making. Comprehensive experiments on benchmark datasets are conducted to evaluate the performance of the proposed attribute fusion-based classifier and the enhanced evidential K-Nearest Neighbors classifier in comparison with both evidential classifiers and conventional machine learning classifiers. The results demonstrate that the proposed classifier outperforms the best existing evidential classifier, achieving an average accuracy improvement of 4.86%, while maintaining low variance, thus confirming its superior effectiveness and robustness.

cs.LG↗

arXiv2024

Isopignistic Canonical Decomposition via Belief Evolution Network

Developing a general information processing model in uncertain environments is fundamental for the advancement of explainable artificial intelligence. Dempster-Shafer theory of evidence is a well-known and effective reasoning method for representing epistemic uncertainty, which is closely related to subjective probability theory and possibility theory. Although they can be transformed to each other under some particular belief structures, there remains a lack of a clear and interpretable transformation process, as well as a unified approach for information processing. In this paper, we aim to address these issues from the perspectives of isopignistic belief functions and the hyper-cautious transferable belief model. Firstly, we propose an isopignistic transformation based on the belief evolution network. This transformation allows for the adjustment of the information granule while retaining the potential decision outcome. The isopignistic transformation is integrated with a hyper-cautious transferable belief model to establish a new canonical decomposition. This decomposition offers a reverse path between the possibility distribution and its isopignistic mass functions. The result of the canonical decomposition, called isopignistic function, is an identical information content distribution to reflect the propensity and relative commitment degree of the BPA. Furthermore, this paper introduces a method to reconstruct the basic belief assignment by adjusting the isopignistic function. It explores the advantages of this approach in modeling and handling uncertainty within the hyper-cautious transferable belief model. More general, this paper establishes a theoretical basis for building general models of artificial intelligence based on probability theory, Dempster-Shafer theory, and possibility theory.

cs.AI↗

arXiv2024

Attribute Fusion-based Evidential Classifier on Quantum Circuits

Dempster-Shafer Theory (DST) as an effective and robust framework for handling uncertain information is applied in decision-making and pattern classification. Unfortunately, its real-time application is limited by the exponential computational complexity. People attempt to address the issue by taking advantage of its mathematical consistency with quantum computing to implement DST operations on quantum circuits and realize speedup. However, the progress so far is still impractical for supporting large-scale DST applications. In this paper, we find that Boolean algebra as an essential mathematical tool bridges the definition of DST and quantum computing. Based on the discovery, we establish a flexible framework mapping any set-theoretically defined DST operations to corresponding quantum circuits for implementation. More critically, this new framework is not only uniform but also enables exponential acceleration for computation and is capable of handling complex applications. Focusing on tasks of classification, we based on a classical attribute fusion algorithm putting forward a quantum evidential classifier, where quantum mass functions for attributes are generated with a simple method and the proposed framework is applied for fusing the attribute evidence. Compared to previous methods, the proposed quantum classifier exponentially reduces the computational complexity to linear. Tests on real datasets validate the feasibility.

quant-ph↗

arXiv2022

BF-QC: Belief Functions on Quantum Circuits

Dempster-Shafer Theory (DST) of belief function is a basic theory of artificial intelligence, which can represent the underlying knowledge more reasonably than Probability Theory (ProbT). Because of the computation complexity exploding exponentially with the increasing number of elements, the practical application scenarios of DST are limited. In this paper, we encode Basic Belief Assignments (BBA) into quantum superposition states and propose the implementation and operation methods of BBA on quantum circuits. We decrease the computation complexity of the matrix evolution on BBA (MEoB) on quantum circuits. Based on the MEoB, we realize the quantum belief functions' implementation, the similarity measurements of BBAs, evidence Combination Rules (CR), and probability transformation on quantum circuits.

quant-ph↗

arXiv2022

Belief Evolution Network-based Probability Transformation and Fusion

Smets proposes the Pignistic Probability Transformation (PPT) as the decision layer in the Transferable Belief Model (TBM), which argues when there is no more information, we have to make a decision using a Probability Mass Function (PMF). In this paper, the Belief Evolution Network (BEN) and the full causality function are proposed by introducing causality in Hierarchical Hypothesis Space (HHS). Based on BEN, we interpret the PPT from an information fusion view and propose a new Probability Transformation (PT) method called Full Causality Probability Transformation (FCPT), which has better performance under Bi-Criteria evaluation. Besides, we heuristically propose a new probability fusion method based on FCPT. Compared with Dempster Rule of Combination (DRC), the proposed method has more reasonable result when fusing same evidence.

cs.AI↗

arXiv2021

Fractal-based Belief Entropy

The total uncertainty measurement of basic probability assignment (BPA) in Dempster-Shafer evidence theory (DSET) has always been an open issue. Although some scholars put forward various measurements and entropies of BPA, due to the existence of discord and non-specificity, there is no method can measure BPA reasonably. In order to utilize BPA to practical decision-making, pignistic probability transformation of BPA is a significant method. In the paper, we simulate the pignistic probability transformation (PPT) process based on the fractal idea, which describes PPT process in detail and shows the process of information volume changes during transformation intuitively. Based on transformation process, we propose a new belief entropy called fractal-based belief (FB) entropy. After verification, FB entropy is superior to all existing belief entropies in terms of total uncertainty measurement and physical model consistency.

cs.IT↗

arXiv2020

Higher order information volume of mass function

For a certain moment, the information volume represented in a probability space can be accurately measured by Shannon entropy. But in real life, the results of things usually change over time, and the prediction of the information volume contained in the future is still an open question. Deng entropy proposed by Deng in recent years is widely applied on measuring the uncertainty, but its physical explanation is controversial. In this paper, we give Deng entropy a new explanation based on the fractal idea, and proposed its generalization called time fractal-based (TFB) entropy. The TFB entropy is recognized as predicting the uncertainty over a period of time by splitting times, and its maximum value, called higher order information volume of mass function (HOIVMF), can express more uncertain information than all of existing methods.

cs.IT↗