Fig. 1 Elicitron’s architecture for requirements elicitation using LLMs: First, LLM agents are generated within a design context in either serial and parallel fashion (incorporating diversity sampling to represent varied user perspectives). These agents then engage in simulated product experience ... More about this image found in Elicitron’s architecture for requirements elicitation using LLMs: First, LL...

Fig. 2 The silhouette score measures the intracluster and intercluster distance. The serial method results in stakeholder embeddings that are more difficult to cluster compared to the parallel and parallel with filtering methods, which indicates that the serial embeddings are more diverse. More about this image found in The silhouette score measures the intracluster and intercluster distance. T...

Fig. 3 Comparison of four groups of users’ embeddings after reducing dimensions to 2 using t-SNE. Group 1: Service and conservation (diamond). Group 2: Outdoor recreation and camping (square). Group 3: Adventure and exploration (triangle). Group 4: Family camping and outdoor activities (circle). T... More about this image found in Comparison of four groups of users’ embeddings after reducing dimensions to...

Fig. 4 Comparison of the average number of latent needs identified by each user agent across the experimental conditions. The error bars indicate standard deviation with n = 20 for each condition. More about this image found in Comparison of the average number of latent needs identified by each user ag...

Fig. 5 Comparative confusion matrices for latent need identification: ( a ) zero-shot classification, ( b ) classification with latent need criteria, and ( c ) classification employing a chain-of-thought approach and latent need criteria More about this image found in Comparative confusion matrices for latent need identification: ( a ) ze...

Fig. 1 The framework of integrating KG, RAG, and LLMs for supply chain discovery More about this image found in The framework of integrating KG, RAG, and LLMs for supply chain discovery

Fig. 2 The concept diagram of the molding sand based on SKOS terminology More about this image found in The concept diagram of the molding sand based on SKOS terminology

Fig. 3 The core classes and relationships in SUDOKN ontology More about this image found in The core classes and relationships in SUDOKN ontology

Fig. 4 Evaluation of entity normalization under different θ values (horizontal axis) More about this image found in Evaluation of entity normalization under different θ values (horizont...

Fig. 5 An example of SCKG in Neo4j More about this image found in An example of SCKG in Neo4j

Fig. 6 Question 1 More about this image found in Question 1

Fig. 7 Question 2 More about this image found in Question 2