{"type":"ScholarlyArticle","title":"LLARS: Enabling Domain Expert & Developer Collaboration for LLM Prompting, Generation and Evaluation","authors":[{"name":"Philipp Steigerwald","slug":"philipp-steigerwald","given":"Philipp","family":"Steigerwald","affiliation":""},{"name":"Mara Stieler","slug":"mara-stieler","given":"Mara","family":"Stieler","affiliation":""},{"name":"Jennifer Burghardt","slug":"jennifer-burghardt","given":"Jennifer","family":"Burghardt","affiliation":""},{"name":"Eric Rudolph","slug":"eric-rudolph","given":"Eric","family":"Rudolph","affiliation":""},{"name":"Jens Albrecht","slug":"jens-albrecht","given":"Jens","family":"Albrecht","affiliation":""}],"abstract":"We demonstrate LLARS, an open-source platform that bridges the gap between domain experts and developers for building LLM-based systems.\r\nLLARS integrates three tightly connected modules into an end-to-end pipeline:\r\nCollaborative Prompt Engineering for real-time co-authoring with version control and instant LLM testing,\r\nBatch Generation for configurable output production across user-selected prompts x models x data with cost control and\r\nHybrid Evaluation where human and LLM evaluators jointly assess outputs through diverse assessment methods, with live agreement metrics and provenance analysis to identify the best model-prompt combination for a given use case.\r\nNew prompts and models are automatically available for batch generation and completed batches can be turned into evaluation scenarios with a single click.\r\nInterviews with six domain experts and three developers in online counselling confirmed that LLARS feels intuitive, saves considerable time by keeping everything in one place and makes interdisciplinary collaboration seamless.\r\nSource code: github.com/th-nuernberg/llars","doi":"10.24963/ijcai.2026/995","url":"https://ijcai.org/proceedings/2026/995","pdf":"https://ijcai.org/proceedings/2026/0995.pdf","markdown":"https://ijcai.org/proceedings/2026/995.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/995","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Demo Track","track":"Demo Track","number":995,"pages":{"first":8526,"last":8529},"keywords":["AI: Natural Language Processing","AI: Humans and AI","AI: Multidisciplinary Topics and Applications"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}