Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Computer Engineering
K-Perm: Personalized Response Generation Using Dynamic Knowledge Retrieval And Persona-Adaptive Queries, Kanak Raj, Kaushik Roy, Vamshi Bonagiri, Priyanshul Govil, Krishnaprasad Thirunarayan, Raxit Goswami, Manas Gaur
K-Perm: Personalized Response Generation Using Dynamic Knowledge Retrieval And Persona-Adaptive Queries, Kanak Raj, Kaushik Roy, Vamshi Bonagiri, Priyanshul Govil, Krishnaprasad Thirunarayan, Raxit Goswami, Manas Gaur
Publications
Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to tend to a user’s persona appropriately. This is particularly crucial for practical applications like mental health support, nutrition planning, culturally sensitive conversations, or reducing toxic behavior in conversational agents. To enhance the relevance and comprehensiveness of personalized responses, we propose using a two-step approach that involves (1) selectively integrating user personas and (2) contextualizing the response with supplementing information from a background knowledge source. We develop K-PERM (Knowledge-guided PErsonalization with Reward Modulation), a dynamic conversational agent that combines these elements. …
Exploring Alternative Approaches To Language Modeling For Learning From Data And Knowledge, Yuxin Zi, Kaushik Roy, Vignesh Narayanan, Amit Sheth
Exploring Alternative Approaches To Language Modeling For Learning From Data And Knowledge, Yuxin Zi, Kaushik Roy, Vignesh Narayanan, Amit Sheth
Publications
Despite their wide applications to language understanding tasks, large language models (LLMs) still face challenges such as hallucinations - the occasional fabrication of information, and alignment issues - the lack of associations with human-curated world models (e.g., intuitive physics or common-sense knowledge). Additionally, the black-box nature of LLMs makes it highly challenging to train them meaningfully in order to achieve a desired behavior. Specifically, the attempt to adjust LLMs’ concept embedding spaces can be highly intractable, which involves analyzing the implicit impact on LLMs’ numerous parameters and the resulting inductive biases. This paper proposes a novel architecture that wraps powerful …