User simulation for evaluating information access systems
With the emergence of various information access systems exhibiting increasing complexity,
there is a critical need for sound and scalable means of automatic evaluation. To address …
there is a critical need for sound and scalable means of automatic evaluation. To address …
Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations
With the aid of large language models, current conversational recommender system (CRS)
has gaining strong abilities to persuade users to accept recommended items. While these …
has gaining strong abilities to persuade users to accept recommended items. While these …
MCKP: Multi-aspect contextual knowledge-enhanced prompting for conversational recommender systems
Empowering conversational recommender systems (CRSs) with knowledge facilitates the
generation of high-quality human-like recommendation proposals to users. Despite …
generation of high-quality human-like recommendation proposals to users. Despite …
Evaluating Conversational Recommender Systems with Large Language Models: A User-Centric Evaluation Framework
Conversational recommender systems (CRS) involve both recommendation and dialogue
tasks, which makes their evaluation a unique challenge. Although past research has …
tasks, which makes their evaluation a unique challenge. Although past research has …
CLICK: Integrating Causal Inference and Commonsense Knowledge Incorporation for Counterfactual Story Generation
Counterfactual reasoning explores what could have happened if the circumstances were
different from what actually occurred. As a crucial subtask, counterfactual story generation …
different from what actually occurred. As a crucial subtask, counterfactual story generation …
Towards Conversational Recommendation in Education: Synthesizing Conversations from Structured Course Data and Benchmarking for Conversational Curriculum …
E Steira - 2024 - ntnuopen.ntnu.no
Conversational Recommender Systems (CRS) introduce a conversational element to
traditional Recommender Systems (RS), allowing for dynamic and interactive …
traditional Recommender Systems (RS), allowing for dynamic and interactive …
Augmentation with Neighboring Information for Conversational Recommendation
Conversational recommender systems (CRSs) suggest items to users by understanding
their needs and preferences from natural language conversations. While users can freely …
their needs and preferences from natural language conversations. While users can freely …