arXiv subjects

He Cheng

Publications and source records attributed to He Cheng.

11 recordsLinked to original sources

arXiv2026

Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models

Biomedical knowledge graphs (KGs) offer structured medical knowledge that can ground large language model (LLM) reasoning in clinical diagnosis application, yet how KG signal should be integrated into LLMs remains an open question. We present a systematic study spanning five KG task formulations, three training paradigms, two KGs, and three base LLMs. At the task level, all paradigms improve over the non-finetuned baseline, but methods with comparable in-domain accuracy show substantially different knowledge transfer behavior. We introduce Gradient Intervention Density (GID) and Gradient Distortion (GD) to measure how broadly an optimizer modifies the pretrained model. GID and GD together reveal a clear divide: KG-judgment training under KL regularization produces sparse, localized updates (a regime we term as surgical alignment), while task-specific SFT produces dense ones. A controlled ablation shows that the objective and KL contribute to sparsity independently, and the paradigms that produce sparse updates also improve reasoning quality, even when their in-domain accuracy is lower than task-specific SFT. Assessing KG-LLM integration thus requires complementing accuracy with optimization-geometry diagnostics. Our implementation can be found at https://github.com/LARK-NLP-Lab/Surgical-Alignment.

cs.CL↗

arXiv2026

LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval

Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in this integration is multi-hop retrieval, yet existing systems struggle to balance efficiency, scalability, and interpretability. We introduce LogosKG, a novel, hardware-aligned framework that enables scalable and interpretable k-hop retrieval on large KGs by building on symbolic KG formulations and executing traversal as hardware-efficient operations over decomposed subject, object, and relation representations. To scale to billion-edge graphs, LogosKG integrates degree-aware partitioning, cross-graph routing, and on-demand caching. Experiments show substantial efficiency gains over CPU and GPU baselines without loss of retrieval fidelity. With proven performance in KG retrieval, a downstream two-round KG-LLM interaction demonstrates how LogosKG enables large-scale, evidence-grounded analysis of how KG topology, such as hop distribution and connectivity, shapes the alignment between structured biomedical knowledge and LLM diagnostic reasoning, thereby opening the door for next-generation KG-LLM integration. The source code is publicly available at https://github.com/LARK-NLP-Lab/LogosKG, and an online demo is available at https://lark-nlp-lab-logoskg.hf.space/.

cs.CL↗

arXiv2025

Advantages and disadvantages of maximally entangled states in dilaton black hole background

We investigate quantum entanglement and coherence for four classes of Bell-like fermionic states in the vicinity of the event horizon of a Garfinkle-Horowitz-Strominger (GHS) dilaton black hole. Contrary to the common expectation that maximally entangled states always provide superior quantum resources, our results show that their entanglement can be lower than that of suitably chosen non-maximally entangled states in this curved spacetime background. This reveals that non-maximally entangled states may offer operational advantages for entanglement-based tasks under gravitational effects. In contrast, quantum coherence exhibits monotonic behavior: larger initial coherence leads to systematically enhanced robustness against the dilaton induced degradation. These results indicate that the optimal choice of initial quantum states depends sensitively on the specific quantum resource, either quantum entanglement or quantum coherence, required for quantum information processing near a dilaton black hole.

gr-qc↗

arXiv2025

Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning

Large language models (LLMs) show promise for diagnostic reasoning but often lack reliable, knowledge grounded inference. Knowledge graphs (KGs), such as the Unified Medical Language System (UMLS), offer structured biomedical knowledge that can support trustworthy reasoning. Prior approaches typically integrate KGs via retrieval augmented generation or fine tuning, inserting KG content into prompts rather than enabling structured reasoning. We explore an alternative paradigm: treating the LLM as a reward model of KG reasoning paths, where the model learns to judge whether a candidate path leads to correct diagnosis for a given patient input. This approach is inspired by recent work that leverages reward training to enhance model reasoning abilities, and grounded in computational theory, which suggests that verifying a solution is often easier than generating one from scratch. It also parallels physicians' diagnostic assessment, where they judge which sequences of findings and intermediate conditions most plausibly support a diagnosis. We first systematically evaluate five task formulation for knowledge path judging and eight training paradigm. Second, we test whether the path judging abilities generalize to downstream diagnostic tasks, including diagnosis summarization and medical question answering. Experiments with three open source instruct-tuned LLMs reveal both promise and brittleness: while specific reward optimization and distillation lead to strong path-judging performance, the transferability to downstream tasks remain weak. Our finding provides the first systematic assessment of "reward model style" reasoning over clinical KGs, offering insights into how structured, reward-based supervision influences diagnostic reasoning in GenAI systems for healthcare.

cs.CL↗

arXiv2025

Polarization-Analyzed Small-Angle Neutron Scattering with an $\textit{in-situ}$ $^{3}$He neutron spin filter at the China Spallation Neutron Source

Polarization-analyzed small-angle neutron scattering (PASANS) is an advanced technique that enables the selective investigation of magnetic scattering phenomena in magnetic materials and distinguishes coherent scattering obscured by incoherent backgrounds, making it particularly valuable for cutting-edge research. The successful implementation of PASANS in China was achieved for the first time at the newly commissioned Very Small Angle Neutron Scattering (VSANS) instrument at the China Spallation Neutron Source (CSNS). This technique employs a combination of a double-V cavity supermirror polarizer and a radio frequency (RF) neutron spin flipper to manipulate the polarization of the incident neutrons. The scattered neutron polarization is stably analyzed by a specially designed $\textit{in-situ}$ optical pumping $^{3}$He neutron spin filter, which covers a spatially symmetric scattering angle coverage of about 4.8 $^{\circ}$. A comprehensive PASANS data reduction method, aimed at pulsed neutron beams, has been established and validated with a silver behenate powder sample, indicating a maximum momentum transfer coverage of approximately 0.25 {\AA} $^{-1}$.

physics.ins-det↗

arXiv2024

BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection

Image anomaly detection (IAD) is essential in applications such as industrial inspection, medical imaging, and security. Despite the progress achieved with deep learning models like Deep Semi-Supervised Anomaly Detection (DeepSAD), these models remain susceptible to backdoor attacks, presenting significant security challenges. In this paper, we introduce BadSAD, a novel backdoor attack framework specifically designed to target DeepSAD models. Our approach involves two key phases: trigger injection, where subtle triggers are embedded into normal images, and latent space manipulation, which positions and clusters the poisoned images near normal images to make the triggers appear benign. Extensive experiments on benchmark datasets validate the effectiveness of our attack strategy, highlighting the severe risks that backdoor attacks pose to deep learning-based anomaly detection systems.

cs.CV↗

arXiv2024

Backdoor Attack against One-Class Sequential Anomaly Detection Models

Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this paper, we explore compromising deep sequential anomaly detection models by proposing a novel backdoor attack strategy. The attack approach comprises two primary steps, trigger generation and backdoor injection. Trigger generation is to derive imperceptible triggers by crafting perturbed samples from the benign normal data, of which the perturbed samples are still normal. The backdoor injection is to properly inject the backdoor triggers to comprise the model only for the samples with triggers. The experimental results demonstrate the effectiveness of our proposed attack strategy by injecting backdoors on two well-established one-class anomaly detection models.

cs.LG↗

arXiv2022

Fine-grained Anomaly Detection in Sequential Data via Counterfactual Explanations

Anomaly detection in sequential data has been studied for a long time because of its potential in various applications, such as detecting abnormal system behaviors from log data. Although many approaches can achieve good performance on anomalous sequence detection, how to identify the anomalous entries in sequences is still challenging due to a lack of information at the entry-level. In this work, we propose a novel framework called CFDet for fine-grained anomalous entry detection. CFDet leverages the idea of interpretable machine learning. Given a sequence that is detected as anomalous, we can consider anomalous entry detection as an interpretable machine learning task because identifying anomalous entries in the sequence is to provide an interpretation to the detection result. We make use of the deep support vector data description (Deep SVDD) approach to detect anomalous sequences and propose a novel counterfactual interpretation-based approach to identify anomalous entries in the sequences. Experimental results on three datasets show that CFDet can correctly detect anomalous entries.

cs.LG↗

arXiv2019

NeuDATool: An Open Source Neutron Data Analysis Tools, Supporting GPU Hardware Acceleration, and Across-computer Cluster Nodes Parallel

Empirical potential structure refinement (EPSR) is a neutron scattering data analysis algorithm and a software package. It was developed by the British spallation neutron source (ISIS) Disordered Materials Group in 1980s, and aims to construct the most-probable atomic structures of disordered liquids. It has been extensively used during the past decades, and has generated reliable results. However, it is programmed in Fortran and implements a shared-memory architecture with OpenMP. With the extensive construction of supercomputer clusters and the widespread use of graphics processing unit (GPU) acceleration technology, it is now necessary to rebuild the EPSR with these techniques in the effort to improve its calculation speed. In this study, an open source framework NeuDATool is proposed. It is programmed in the object-oriented language C++, can be paralleled across nodes within a computer cluster, and supports GPU acceleration. The performance of NeuDATool has been tested with water and amorphous silica neutron scattering data. The test shows that the software could reconstruct the correct microstructure of the samples, and the calculation speed with GPU acceleration could increase by more than 400 times compared with CPU serial algorithm at a simulation box consists about 100 thousand atoms. NeuDATool provides another choice for scientists who are familiar with C++ programming and want to define specific models and algorithms for their analyses.

physics.comp-ph↗

arXiv2018

Water/Cosolvent Attraction Induced Phase Separation: a Molecular Picture of Cononsolvency

Cononsolvency is a phenomenon for which the solubility of a macromolecule decreases or even vanishes in the mixture of two good solvents. Although it has been widely applied in physicochemical, green chemical and pharmaceutical industry, its origin is still under active debate. Here, by using combined neutron total scattering, deuterium-labelling and all-atom molecular dynamic simulations, we demonstrated that it is the strong water/cosolvent attraction that leads to the cononsolvency. The combined approach presented here has opened a new route for investigating the most probable all-atom structure in macromolecular solutions and the thermodynamic origin of solubilities.

cond-mat.soft↗

arXiv2016

Development and prospect of Very Small Angle Neutron Scattering (VSANS) Techniques

Very Small Angle Neutron Scattering (VSANS) is an upgrade of the traditional Small Angle Neutron Scattering (SANS) technique which can cover three orders of magnitude of length scale from one nanometer to one micrometer. It is a powerful tool for structure calibration in polymer science, biology, material science and condensed matter physics. Since the first VSANS instrument, D11 in Grenoble, was built in 1972, new collimation techniques, focusing optics (multi-beam converging apertures, material or magnetic lenses, and focusing mirrors) and higher resolution detectors combined with the long flight paths and long incident neutron wavelengths have been developed. In this paper, a detailed review is given of the development, principles and application conditions of various VSANS techniques. Then, beam current gain factors are calculated to evaluate those techniques. A VSANS design for the China Spallation Neutron Source (CSNS) is thereby presented.

physics.ins-det↗