arXiv subjects

Wenhao Song

Publications and source records attributed to Wenhao Song.

8 recordsLinked to original sources

arXiv2026

ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chains

Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for Question Answering (QA) by integrating external information into Large Language Models (LLMs). However, false, inaccurate, and misleading information in news and social media poses a serious challenge to real-world RAG systems, especially in multi-hop QA, where complex multi-step reasoning can be misled by even a single deceptive misinformation segment in the retrieved documents. Existing approaches mainly rely on implicit alignment or explicit regulation, but their limited ability to assess fine-grained information reliability makes them vulnerable to deceptive misinformation that is semantically relevant to the question yet factually incorrect, leading to erroneous answers. To address this limitation, we propose ReliableRAG, which, to the best of our knowledge, is the first reliability-driven framework that mitigates deceptive misinformation in multi-hop QA through fine-grained evaluation of individual triples. ReliableRAG first extracts information segments from source documents and represents them as structured triples. It then quantifies triple reliability by combining query-triple semantic relevance with triple credibility, retaining only the top-$K$ reliable and non-redundant triples. Based on these refined triples, ReliableRAG autoregressively constructs robust reasoning chains to consolidate trustworthy evidence and filter deceptive misinformation, producing accurate answers faithful to reliable information. Experiments on three multi-hop QA datasets show that ReliableRAG outperforms existing methods, substantially improving the factual reliability and robustness of RAG systems under deceptive misinformation injection.

cs.CL↗

arXiv2026

Exact Algorithms for Edge Deletion to Cactus Graphs and Weighted Variants

We study exact exponential-time algorithms for Edge Deletion to Cactus. Given a connected graph $G$, the task is to delete a minimum number of edges so that the remaining spanning graph is a connected cactus. Akhtar and Philip (IWOCA 2026) gave an $O^*(3^n)$-time algorithm for the unweighted problem, where $n$ is the number of vertices in the input graph and the $O^*(\cdot)$ notation hides polynomial factors. We improve this bound to $O^*(2^n)$ time and space. More generally, if the deletion costs take at most $q$ distinct nonnegative real values, then the weighted problem can be solved in $O^*(2^n n^{O(q)})$ time and space. Thus every fixed number of distinct costs, and in particular the unweighted case, admits a faster exact algorithm. For nonnegative integer costs of total weight $W$, we obtain an $O^*(2^n(W+1))$ pseudo-polynomial algorithm, while arbitrary nonnegative real costs admit an $O^*(3^n)$ exact algorithm.

cs.DS↗

arXiv2026

Closed Expressions for the Weight Distributions of Codes Associated with Perfect Codes

Perfect codes are arguably the most fascinating structures in combinatorial coding theory, and their classification and weight distribution are of considerable interest. This classification also involves the analysis of some related structures. This paper considers five closely related structures, but all of them have never been tied together before. These structures are 1-perfect codes, extended 1-perfect codes, nearly perfect 1-covering codes, extended nearly perfect 1-covering codes, and one family of completely regular codes (to be called diamond codes). The current work concentrates on the weight distributions of these five families of codes. In the past, some of these weight distributions were not computed, some required heavy tools, and for some only the weight enumerator was presented. We provide complete weight distributions for all five families using some methods that do not require any heavy tools.

math.CO↗

arXiv2025

New characterization of full weight spectrum one-orbit cyclic subspace codes

Castello $\textit{et al}$. [J. Comb. Theory Ser. A, 212, 106005 (2025)] provided a complete classification for full weight spectrum (FWS) one-orbit cyclic subspace codes. In this paper, we determine the weight distributions of a family of FWS codes and exhibit some equivalence classes of FWS codes under certain conditions. Furthermore, we provide a complete classification for $r$-FWS codes.

cs.CR↗

arXiv2025

Towards Efficient Few-shot Graph Neural Architecture Search via Partitioning Gradient Contribution

To address the weight coupling problem, certain studies introduced few-shot Neural Architecture Search (NAS) methods, which partition the supernet into multiple sub-supernets. However, these methods often suffer from computational inefficiency and tend to provide suboptimal partitioning schemes. To address this problem more effectively, we analyze the weight coupling problem from a novel perspective, which primarily stems from distinct modules in succeeding layers imposing conflicting gradient directions on the preceding layer modules. Based on this perspective, we propose the Gradient Contribution (GC) method that efficiently computes the cosine similarity of gradient directions among modules by decomposing the Vector-Jacobian Product during supernet backpropagation. Subsequently, the modules with conflicting gradient directions are allocated to distinct sub-supernets while similar ones are grouped together. To assess the advantages of GC and address the limitations of existing Graph Neural Architecture Search methods, which are limited to searching a single type of Graph Neural Networks (Message Passing Neural Networks (MPNNs) or Graph Transformers (GTs)), we propose the Unified Graph Neural Architecture Search (UGAS) framework, which explores optimal combinations of MPNNs and GTs. The experimental results demonstrate that GC achieves state-of-the-art (SOTA) performance in supernet partitioning quality and time efficiency. In addition, the architectures searched by UGAS+GC outperform both the manually designed GNNs and those obtained by existing NAS methods. Finally, ablation studies further demonstrate the effectiveness of all proposed methods.

cs.LG↗

arXiv2025

FT-MoE: Sustainable-learning Mixture of Experts for Fault-Tolerant Computing

Intelligent fault-tolerant (FT) computing has recently demonstrated significant advantages in predicting and diagnosing faults proactively, thereby ensuring reliable service delivery. However, due to the heterogeneity of fault knowledge, dynamic workloads, and limited data support, existing deep learning-based FT algorithms face challenges in fault detection quality and training efficiency. This is primarily because their homogenization of fault knowledge perception difficuties to fully capture diverse and complex fault patterns. To address these challenges, we propose FT-MoE, a sustainable-learning fault-tolerant computing framework based on a dual-path architecture for high-accuracy fault detection and classification. This model employs a mixture-of-experts (MoE) architecture, enabling different parameters to learn distinct fault knowledge. Additionally, we adopt a two-stage learning scheme that combines comprehensive offline training with continual online tuning, allowing the model to adaptively optimize its parameters in response to evolving real-time workloads. To facilitate realistic evaluation, we construct a new fault detection and classification dataset for edge networks, comprising 10,000 intervals with fine-grained resource features, surpassing existing datasets in both scale and granularity. Finally, we conduct extensive experiments on the FT benchmark to verify the effectiveness of FT-MoE. Results demonstrate that our model outperforms state-of-the-art methods.

cs.LG↗

arXiv2020

Gate-tunable van der Waals heterostructure for reconfigurable neural network vision sensor

Early processing of visual information takes place in the human retina. Mimicking neurobiological structures and functionalities of the retina provide a promising pathway to achieving vision sensor with highly efficient image processing. Here, we demonstrate a prototype vision sensor that operates via the gate-tunable positive and negative photoresponses of the van der Waals (vdW) vertical heterostructures. The sensor emulates not only the neurobiological functionalities of bipolar cells and photoreceptors but also the unique synaptic connectivity between bipolar cells and photoreceptors. By tuning gate voltage for each pixel, we achieve reconfigurable vision sensor for simultaneously image sensing and processing. Furthermore, our prototype vision sensor itself can be trained to classify the input images, via updating the gate voltages applied individually to each pixel in the sensor. Our work indicates that vdW vertical heterostructures offer a promising platform for the development of neural network vision sensor.

cond-mat.mtrl-sci↗

arXiv2018

Long short-term memory networks in memristor crossbars

Recent breakthroughs in recurrent deep neural networks with long short-term memory (LSTM) units has led to major advances in artificial intelligence. State-of-the-art LSTM models with significantly increased complexity and a large number of parameters, however, have a bottleneck in computing power resulting from limited memory capacity and data communication bandwidth. Here we demonstrate experimentally that LSTM can be implemented with a memristor crossbar, which has a small circuit footprint to store a large number of parameters and in-memory computing capability that circumvents the 'von Neumann bottleneck'. We illustrate the capability of our system by solving real-world problems in regression and classification, which shows that memristor LSTM is a promising low-power and low-latency hardware platform for edge inference.

cs.ET↗