5 papers
Internal Representation, Not Clinical Knowledge: Where Apparent LLM Triage Failures Originate
David Fraile Navarro, Berardino Como, Jialei Sheng +2
Patient-voiced clinical-triage benchmarks report high under-triage rates for consumer LLMs for constrained multiple-choice output, yet the same cases score differently with free-te…
Recommendation-as-Experience: A framework for context-sensitive adaptation in conversational recommender systems
Raj Mahmud, Shlomo Berkovsky, Mukesh Prasad +1
While Conversational Recommender Systems (CRS) have matured technically, they frequently lack principled methods for encoding latent experiential aims as adaptive state variables.…
Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering
Yu Takahashi, Shun Takeuchi, Kexuan Xin +6
Question answering (QA) systems are increasingly deployed across domains. However, their reliability is undermined when retrieved evidence is incomplete, noisy, or uncertain. Exist…
Evaluating User Experience in Conversational Recommender Systems: A Systematic Review Across Classical and LLM-Powered Approaches
Raj Mahmud, Yufeng Wu, Abdullah Bin Sawad +3
Conversational Recommender Systems (CRSs) are receiving growing research attention across domains, yet their user experience (UX) evaluation remains limited. Existing reviews large…
Understanding User Preferences for Interaction Styles in Conversational Recommender Systems: The Predictive Role of System Qualities, User Experience, and Traits
Raj Mahmud, Shlomo Berkovsky, Mukesh Prasad +1
Conversational Recommender Systems (CRSs) deliver personalised recommendations through multi-turn natural language dialogue and increasingly support both task-oriented and explorat…