Authors:
Chukwuka Victor Obionwu
1
;
Bhavya Valappil
1
;
Minu Genty
1
;
Maria Jomy
1
;
Visakh Padmanabhan
1
;
Aishwarya Suresh
1
;
Sumat Bedi
1
;
David Broneske
2
and
Gunter Saake
1
Affiliations:
1
University of Magdeburg, Magdeburg, Germany
;
2
German Centre for Higher Education Research and Science Studies, Hannover, Germany
Keyword(s):
Information Retrieval, Generative AI, Knowledge Graphs, Intent Classification, Conversational Agents, Instructional Feedback.
Abstract:
The interaction between students and instructors can be likened to an interaction with a conversational agent model that understands the context of the interaction and the questions the student poses. Large language models have exhibited remarkable aptitude for facilitating learning and educational procedures. However, they occasionally exhibit hallucinations, which can result in the spread of inaccurate or false information. This issue is problematic and requires attention in order to ensure the general reliability of the information system. Knowledge graphs provide a methodical technique for describing entities and their interconnections. This facilitates a comprehensive and interconnected understanding of the knowledge in a specific field. Therefore, in order to make the interactions with our conversational agent more human-like and to deal with hallucinations, we employ a retrieval-focused generation strategy that utilizes existing knowledge and creates responses based on context
ually relevant information. Our system relies on a knowledge graph, an intent classifier, and a response generator that compares and evaluates question embeddings to ensure accurate and contextually appropriate replies. We further evaluate our implementation based on relevant metrics and compare it to state-of-the-art task-specific retrieve-and-extract architectures. For language generation tasks, we find that the RCG models generate more specific, diverse, and factual information than state-of-the-art baseline models.
(More)