Goal Model
A modeling tool in requirements engineering and business analysis that represents organizational intentions hierarchically as goals, sub-goals, and their dependencies. Common forms include the i* framework and the KAOS method, used to guide system analysis and design.
Timeline (last 90 days)
The method first builds a goal model for the organization, pre-defining the axes of classification (classification dimensions and criteria) rather than passively discovering them from the data.
The paper has LLMs interpret the textual narrative of each variant in the context of the goal model and assign it to the most appropriate category, using the LLM's semantic reasoning capability to connect low-level process behavior with high-level business objectives.
Goal models are established tools in requirements engineering and business analysis, with common forms including the i* framework and the KAOS method.
The cost of the method is the additional effort required to construct the goal model, which is an upfront cost that must be paid compared to automatic clustering.
Co-design treats the draft model and the target model as an integrated system to be designed and trained from the outset, in order to improve the token acceptance rate.
All Facts (5)
The method first builds a goal model for the organization, pre-defining the axes of classification (classification dimensions and criteria) rather than passively discovering them from the data.
50%UnverifiedThe paper has LLMs interpret the textual narrative of each variant in the context of the goal model and assign it to the most appropriate category, using the LLM's semantic reasoning capability to connect low-level process behavior with high-level business objectives.
50%UnverifiedGoal models are established tools in requirements engineering and business analysis, with common forms including the i* framework and the KAOS method.
50%UnverifiedThe cost of the method is the additional effort required to construct the goal model, which is an upfront cost that must be paid compared to automatic clustering.
50%UnverifiedCo-design treats the draft model and the target model as an integrated system to be designed and trained from the outset, in order to improve the token acceptance rate.
50%