{"version":1,"type":"story","url":"https://digestai.news/story/researchers-propose-goal-driven-variant-categorization-using-llm","json":"https://digestai.news/story/researchers-propose-goal-driven-variant-categorization-using-llm.json","markdown":"https://digestai.news/story/researchers-propose-goal-driven-variant-categorization-using-llm.md","slug":"researchers-propose-goal-driven-variant-categorization-using-llm","headline":"Researchers propose Goal-driven variant categorization using LLM","summary":"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 a textual narrative describing its behavior, and a large language model interprets the narrative in the context of the goal model to assign the variant to the most suitable category.\n\nThe 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.","keyPoints":["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"],"whyItMatters":"By aligning process variant categorization with explicit business goals, the method reduces manual interpretation, improves consistency across large variant sets, and offers a systematic way to adjust categories when goals change.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["LLM"],"people":[]},"firstPublishedAt":"2026-09-22T04:00:00Z","updatedAt":"2026-09-22T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Goal-driven Variant Categorization","url":"https://arxiv.org/abs/2609.22475","publishedAt":"2026-09-22T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers propose Goal-driven variant categorization using LLM\", 22 September 2026, https://digestai.news/story/researchers-propose-goal-driven-variant-categorization-using-llm","publisher":"Digest AI","title":"Researchers propose Goal-driven variant categorization using LLM","datePublished":"2026-09-22T04:00:00Z","url":"https://digestai.news/story/researchers-propose-goal-driven-variant-categorization-using-llm"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}