On the Effectiveness of Artificial Intelligence Technologies in Forensic Examinations

The article describes a set of methods and algorithms that form the basis of artificial intelligence technologies and examines their characteristics and technical features of functioning in relation to solving tasks in criminalistics and forensic expertology. Based on the distinction between artificial intelligence technologies for “general” use and highly specialized technologies, the limits of their application in practical activities are defined.Using examples of “general” use technologies (ChatGPT, Alice AI, Grok, and Qwen Chat), their low effectiveness is demonstrated in terms of studying document details to identify the writing materials by the provided digital image of a handwritten text fragment as well as by the verbal description of a specific writing material as a combination of specific features.Based on the results of a comprehensive analysis of the experimentally obtained data, it is concluded that the technological capabilities of these tools in forensic examination are highly limited when solving tasks aimed at determining the reference group of writing materials. At the same time attention is drawn to the importance of using modern, highly specialized technologies developed for a specific expert task provided that the relevant software will not be the sole means of examination and will be used exclusively by the experts competent in their field and the results of such programs are evaluated based on the expert’s specialized knowledge.

Authors

Institutions

Publication Details

Journal
Theory and Practice of Forensic Science
Published
2026-11-16
DOI
https://doi.org/10.30764/1819-2785-2026-3-74-85
Primary Topic
Handwritten Text Recognition Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

On the Effectiveness of Artificial Intelligence Technologies in Forensic Examinations

A. F. Kupin, A. S. Kovalenko
4 links
Theory and Practice of Forensic Science
Handwritten Text Recognition Techniques
article

On the Effectiveness of Artificial Intelligence Technologies in Forensic Examinations

A. F. Kupin, A. S. Kovalenko
article en

Abstract

The article describes a set of methods and algorithms that form the basis of artificial intelligence technologies and examines their characteristics and technical features of functioning in relation to solving tasks in criminalistics and forensic expertology. Based on the distinction between artificial intelligence technologies for “general” use and highly specialized technologies, the limits of their application in practical activities are defined.Using examples of “general” use technologies (ChatGPT, Alice AI, Grok, and Qwen Chat), their low effectiveness is demonstrated in terms of studying document details to identify the writing materials by the provided digital image of a handwritten text fragment as well as by the verbal description of a specific writing material as a combination of specific features.Based on the results of a comprehensive analysis of the experimentally obtained data, it is concluded that the technological capabilities of these tools in forensic examination are highly limited when solving tasks aimed at determining the reference group of writing materials. At the same time attention is drawn to the importance of using modern, highly specialized technologies developed for a specific expert task provided that the relevant software will not be the sole means of examination and will be used exclusively by the experts competent in their field and the results of such programs are evaluated based on the expert’s specialized knowledge.

Theory and Practice of Forensic ScienceVol. 21(3)
Bauman Moscow State Technical University (RU), Moscow Academy of the Investigative Committee of the Russian Federation (RU)
Handwritten Text Recognition Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon