Researchers propose Goal-driven variant categorization using LLM
The paper tackles the challenge of clustering process variants into business‑meaningful categories. Traditional methods cluster based on structural similarity, then analysts manually map clusters to goals, a step that becomes hard as variant numbers grow. The authors introduce a goal‑driven workflow: first an organization’s goal model defines the categorization axis. Each variant is turned into…
Key points
- goal-driven variant categorization uses a goal model to guide llm-based classification
- variants are converted to textual narratives for llm interpretation
- evaluation on three public logs shows partitions that differ from unguided induction and react to goal edits
The authors evaluate the approach on three public process logs that vary in scale and behavioral diversity. Results show that goal‑model guidance produces partitions that differ from unguided induction and respond to controlled edits of the declared alternatives, though it requires the upfront effort of authoring a goal model.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- Researchers propose multi-split boundary decision to lower LLM document segmentation cost · 1 src
- GaitVista reduces gait measurement error by 27.7% in lab tests · 1 src
- Megagon Labs releases mawile workbench for auditing LLM judges · 1 src
- AutoGym framework generates verifiable agent gyms · 1 src
- EvidenT improves enterprise assistant evidence verification by 29% · 1 src
Comments
via GitHub Discussions