LLM-Driven Event Log Generation from Forensic Cases: A Comparative Study of ChatGPT, Claude, and Gemini
Bibliographic record
Abstract
Event logs underpin both process mining and digital forensic analysis. Yet turning unstructured case narratives into wellformed logs remains a non-trivial task. Much of the work to date has relied on bespoke Natural Language Processing (NLP) pipelines or transformer-based stacks, which are solutions that can be effective but are also engineering-intensive. This study asks a straightforward question: can large language models (LLMs) (ChatGPT, Claude, and Gemini, produce structured, XES-compatible event logs directly from forensic narratives? We examine eight case files and assess the outputs along four dimensions that matter in practice: temporal consistency, redundancy, schema compliance, and classification performance. The results are instructive. ChatGPT generated timelines that were fully consistent and adhered to the schema in all cases. Claude performed well overall but showed slightly lower consistency and compliance. Gemini achieved near-perfect temporal alignment, though its outputs varied more across cases. Pairwise comparisons indicate small but meaningful gaps in consistency. Taken together, these findings suggest that LLMs are a potential alternative to custom pipelines for event log generation. Even so, the forensic context warrants caution: outputs should be validated carefully before use, with attention to case details and downstream impact.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".