Danila Katalshov

Mr. Danila Katalshov

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 June 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
OSOlga Shvetsova
Olga Shvetsova
DKDanila Katalshov
Danila Katalshov
SLSang-Kon Lee
Sang-Kon Lee
This paper proposes a technological framework designed to mitigate the inherent risks associated with the deployment of artificial intelligence (AI) in decision-making and task execution within the management processes. The Agreement Validation Interface (AVI) functions as a modular Application Programming Interface (API) Gateway positioned between user applications and LLMs. This gateway architecture is designed to be LLM-agnostic, meaning it can operate with various underlying LLMs without requiring specific modifications for each model. This universality is achieved by standardizing the interface for requests and responses and applying a consistent set of validation and enhancement processes irrespective of the chosen LLM provider, thus offering a consistent governance layer across a diverse LLM ecosystem. AVI facilitates the orchestration of multiple AI subcomponents for input–output validation, response evaluation, and contextual reasoning, thereby enabling real-time, bidirectional filtering of user interactions. A proof-of-concept (PoC) implementation of AVI was developed and rigorously evaluated using industry-standard benchmarks. The system was tested for its effectiveness in mitigating adversarial prompts, reducing toxic outputs, detecting personally identifiable information (PII), and enhancing factual consistency. The results demonstrated that AVI reduced successful fast injection attacks by 82%, decreased toxic content generation by 75%, and achieved high PII detection performance (F1-score ≈ 0.95). Furthermore, the contextual reasoning module significantly improved the neutrality and factual validity of model outputs. Although the integration of AVI introduced a moderate increase in latency, the overall framework effectively enhanced the reliability, safety, and interpretability of LLM-driven applications. AVI provides a scalable and adaptable architectural template for the responsible deployment of generative AI in high-stakes domains such as finance, healthcare, and education, promoting safer and more ethical use of AI technologies.

15 May 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
OSOlga Shvetsova
Olga Shvetsova
DKDanila Katalshov
Danila Katalshov
SLSang-Kon Lee
Sang-Kon Lee
This paper proposes a technological framework designed to mitigate the inherent risks associated with the deployment of artificial intelligence (AI) in decision-making and task execution within the management processes. The Agreement Validation Interface (AVI)—a modular, LLM-agnostic API gateway - has been designed to enhance the trustworthiness and governance of generative AI systems. AVI facilitates orchestration of multiple AI subcomponents for input-output validation, response evaluation, and contextual reasoning, thereby enabling real-time, bidirectional filtering of user interactions. A proof-of-concept (PoC) implementation of AVI was developed and rigorously evaluated using industry-standard benchmarks. The system was tested for its effectiveness in mitigating adversarial prompts, reducing toxic outputs, detecting personally identifiable information (PII), and enhancing factual consistency. Results demonstrated that AVI reduced successful fast injection attacks by 82%, decreased toxic content generation by 75%, and achieved high PII detection performance (F1 score ≈ 0.95). Furthermore, the contextual reasoning module significantly improved the neutrality and factual validity of model outputs. Although the integration of AVI introduced a moderate increase in latency, the overall framework effectively enhanced the reliability, safety, and interpretability of LLM-driven applications. AVI provides a scalable and adaptable architectural template for the responsible deployment of generative AI in high-stakes domains such as finance, healthcare, and education, promoting safer and more ethical use of AI technologies.

15 May 2026 in Electronics
Verified
Journal Article
Open access
PDF file
DKDanila Katalshov
Danila Katalshov
OSOlga Shvetsova
Olga Shvetsova
SLSang-Kon Lee
Sang-Kon Lee
SKSviatlana Koltun
Sviatlana Koltun
The widespread adoption of Generative Artificial Intelligence (GenAI) in regulated enterprises is currently hindered by the “Static Alignment Trap”: the inability of traditional safety methods, such as Reinforcement Learning from Human Feedback (RLHF), to adapt to rapidly shifting compliance landscapes without costly retraining. This paper introduces and evaluates the Agreement Validation Interface (AVI), a modular governance architecture that functions as a deterministic middleware layer. By decoupling governance from the core inference engine, AVI implements Dynamic Bilateral Alignment (DBA), enforcing policy constraints at both the input and output stages through vector-based semantic retrieval. Adopting a Design Science Research (DSR) methodology, we validated the system against the FinanceBench financial benchmark (N=150 queries, three repeated runs, 450 total observations) and a proprietary Russian-language provocative content dataset developed internally at MWS AI (N=201 queries; not publicly available). The empirical results demonstrate that the architecture achieves an 83.2% Large Language Model (LLM)-judge compliance rate (95% confidence interval, CI: 79.4–87.1%), statistically significantly exceeding the unfiltered baseline of 63.7% (Δ=+19.5 percentage points (pp), t=4.02, p=0.002). The vector-based input filter achieves perfect detection performance (Precision =1.000, Recall =1.000, F1 =1.000). Cross-domain validation on 201 Russian-language provocative queries confirms generalizability (Recall =0.985, LLM compliance among triggered queries =0.977). The operational Time-to-Compliance for enforcing new rules was reduced from hours (model fine-tuning) to under five seconds (vector indexing). These findings suggest that enterprise AI safety requires an architectural shift from model-centric training to system-centric control, complemented by system-prompt-level anti-inference governance. We conclude that AVI offers a scalable, cost-effective, and statistically validated framework for auditable AI compliance, independent of the underlying model provider.