Selected work

Representative Papers

Double-Scoring: Reliable Extraction of Strong Lottery Tickets

Jul 15, 2026

Existing methods struggle to reliably extract strong lottery ticket subnetworks from randomly initialized networks. This work proposes a dual-scoring mechanism that introduces an expanded scoring tensor space to optimize mask selection under fixed sparsity, effectively reformulating sparse structure discovery as an edge-popup optimization problem on a zero-augmented network. The approach preserves the reachability of original masks and substantially reduces sensitivity to sparsity hyperparameters by employing frozen-weight scoring during training alongside fixed-density mask optimization. Experimental results demonstrate that the method significantly outperforms fixed-density Edge-Popup, initialization-based pruning, and retrospective sparse training approaches across multiple benchmarks, while exhibiting strong robustness to variations in sparsity settings.

0 citationsRead paper

Security Threats and Their Impact on Blockchain Interoperability: Identification and Countermeasures

Jun 12, 2026

Blockchain interoperability has led to the loss of hundreds of millions of dollars in assets due to the absence of systematic security mechanisms. This work proposes the first five-dimensional threat taxonomy specifically tailored for cross-chain interoperability, encompassing core chain attacks, network-level attacks, interoperability-specific exploits, social engineering, and smart contract vulnerabilities. By integrating systematic threat modeling, attack surface analysis, and smart contract security evaluation methodologies, the study provides a comprehensive examination of the attack surfaces associated with each threat category. Building upon this analysis, the authors establish a structured mapping framework that links identified threats to corresponding defense strategies, yielding a formalized security guideline. This framework offers both theoretical foundations and practical guidance for designing and evaluating secure and reliable blockchain interoperability solutions.

0 citationsRead paper

AI-Driven Test Case Generation from Natural Language Requirements: A Survey of Techniques and Research Gaps

Jun 04, 2026

This study addresses the challenges of automatically generating test cases from natural language requirements—namely semantic ambiguity, weak traceability, and inconsistent evaluation—which hinder existing approaches from achieving a balance among automation, accuracy, and reliability. Through a systematic literature review conducted in accordance with the Kitchenham and Charters guidelines, the authors analyze AI- and NLP-driven research from 2000 to 2025, proposing a three-phase evolutionary framework and introducing a novel six-dimensional quality gap analysis encompassing automation, ambiguity handling, domain applicability, traceability, evaluation adequacy, and hallucination control. An examination of 21 core studies reveals that current methods fail to simultaneously satisfy all six dimensions. Based on these findings, the paper outlines four actionable research directions: hallucination mitigation, enhanced traceability, complexity-aware modeling, and compliance assurance.

0 citationsRead paper

Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation

Jun 03, 2026

This work addresses the challenge of cascading hallucinations in multi-step agent-based RAG systems, where early errors propagate confidently yet factually incorrect outputs, and existing approaches struggle to detect such failures effectively. The study formalizes cascading hallucination as a distinct failure mode and introduces CHARM—a lightweight, plug-and-play framework that mitigates error propagation through four mechanisms: stage-level factual verification, cross-stage consistency tracking, confidence propagation monitoring, and cascade-aware resolution triggering. Experimental results demonstrate that CHARM achieves an 89.4% detection rate for cascading errors with a low false positive rate of 5.3%, reduces error propagation by 82.1%, and incurs only a modest average latency increase of 215ms per reasoning stage across multiple multi-hop question answering benchmarks, substantially outperforming baseline methods that solely inspect final outputs.

0 citationsRead paper

A Multi-Layer Testing Framework for Automated Data Quality Assurance in Cloud-Native ELT Pipelines

May 19, 2026

This study addresses the critical data quality challenges in cloud-native ELT pipelines arising from heterogeneous data sources, schema evolution, and multi-backend environments. The authors propose a multi-layered testing framework that integrates orchestration-level validation, declarative dbt tests, LLM-generated semantic tests, and cross-storage consistency verification between DuckDB and Snowflake, all unified under Apache Airflow scheduling. Notably, this work pioneers the incorporation of LLM-driven semantic testing into production-grade ELT workflows. In anomaly injection experiments, the framework achieves a 128.57% improvement in detection rate, successfully identifying all 16 injected anomalies. Furthermore, three critical tables exhibit perfect consistency across both storage systems, with the end-to-end pipeline completing in just 106.58 seconds, substantially enhancing both detection coverage and engineering feasibility.

0 citationsRead paper

Recent publications

Latest Papers

Double-Scoring: Reliable Extraction of Strong Lottery Tickets

Jul 15, 2026

Existing methods struggle to reliably extract strong lottery ticket subnetworks from randomly initialized networks. This work proposes a dual-scoring mechanism that introduces an expanded scoring tensor space to optimize mask selection under fixed sparsity, effectively reformulating sparse structure discovery as an edge-popup optimization problem on a zero-augmented network. The approach preserves the reachability of original masks and substantially reduces sensitivity to sparsity hyperparameters by employing frozen-weight scoring during training alongside fixed-density mask optimization. Experimental results demonstrate that the method significantly outperforms fixed-density Edge-Popup, initialization-based pruning, and retrospective sparse training approaches across multiple benchmarks, while exhibiting strong robustness to variations in sparsity settings.

0 citationsRead paper

Security Threats and Their Impact on Blockchain Interoperability: Identification and Countermeasures

Jun 12, 2026

Blockchain interoperability has led to the loss of hundreds of millions of dollars in assets due to the absence of systematic security mechanisms. This work proposes the first five-dimensional threat taxonomy specifically tailored for cross-chain interoperability, encompassing core chain attacks, network-level attacks, interoperability-specific exploits, social engineering, and smart contract vulnerabilities. By integrating systematic threat modeling, attack surface analysis, and smart contract security evaluation methodologies, the study provides a comprehensive examination of the attack surfaces associated with each threat category. Building upon this analysis, the authors establish a structured mapping framework that links identified threats to corresponding defense strategies, yielding a formalized security guideline. This framework offers both theoretical foundations and practical guidance for designing and evaluating secure and reliable blockchain interoperability solutions.

0 citationsRead paper

AI-Driven Test Case Generation from Natural Language Requirements: A Survey of Techniques and Research Gaps

Jun 04, 2026

This study addresses the challenges of automatically generating test cases from natural language requirements—namely semantic ambiguity, weak traceability, and inconsistent evaluation—which hinder existing approaches from achieving a balance among automation, accuracy, and reliability. Through a systematic literature review conducted in accordance with the Kitchenham and Charters guidelines, the authors analyze AI- and NLP-driven research from 2000 to 2025, proposing a three-phase evolutionary framework and introducing a novel six-dimensional quality gap analysis encompassing automation, ambiguity handling, domain applicability, traceability, evaluation adequacy, and hallucination control. An examination of 21 core studies reveals that current methods fail to simultaneously satisfy all six dimensions. Based on these findings, the paper outlines four actionable research directions: hallucination mitigation, enhanced traceability, complexity-aware modeling, and compliance assurance.

0 citationsRead paper

Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation

Jun 03, 2026

This work addresses the challenge of cascading hallucinations in multi-step agent-based RAG systems, where early errors propagate confidently yet factually incorrect outputs, and existing approaches struggle to detect such failures effectively. The study formalizes cascading hallucination as a distinct failure mode and introduces CHARM—a lightweight, plug-and-play framework that mitigates error propagation through four mechanisms: stage-level factual verification, cross-stage consistency tracking, confidence propagation monitoring, and cascade-aware resolution triggering. Experimental results demonstrate that CHARM achieves an 89.4% detection rate for cascading errors with a low false positive rate of 5.3%, reduces error propagation by 82.1%, and incurs only a modest average latency increase of 215ms per reasoning stage across multiple multi-hop question answering benchmarks, substantially outperforming baseline methods that solely inspect final outputs.

0 citationsRead paper

A Multi-Layer Testing Framework for Automated Data Quality Assurance in Cloud-Native ELT Pipelines

May 19, 2026

This study addresses the critical data quality challenges in cloud-native ELT pipelines arising from heterogeneous data sources, schema evolution, and multi-backend environments. The authors propose a multi-layered testing framework that integrates orchestration-level validation, declarative dbt tests, LLM-generated semantic tests, and cross-storage consistency verification between DuckDB and Snowflake, all unified under Apache Airflow scheduling. Notably, this work pioneers the incorporation of LLM-driven semantic testing into production-grade ELT workflows. In anomaly injection experiments, the framework achieves a 128.57% improvement in detection rate, successfully identifying all 16 injected anomalies. Furthermore, three critical tables exhibit perfect consistency across both storage systems, with the end-to-end pipeline completing in just 106.58 seconds, substantially enhancing both detection coverage and engineering feasibility.

0 citationsRead paper