253 citations · 414 across the 5 of their papers we have counts for
5 papers
LLMs Infer Cultural Context but Fail to Apply It When Responding
Yisong Miao, Jian Zhu, Vered Shwartz
Recent work has shown that LLMs overrepresent dominant cultures, particularly Western ones, while marginalizing others. We investigate whether this affects models' ability to gener…
Discursive Circuits: How Do Language Models Understand Discourse Relations?
Yisong Miao, Min-Yen Kan
Which components in transformer language models are responsible for discourse understanding? We hypothesize that sparse computational graphs, termed as discursive circuits, control…
Comparative Snippet Generation
Saurabh Jain, Yisong Miao, Min-Yen Kan
We model product reviews to generate comparative responses consisting of positive and negative experiences regarding the product. Specifically, we generate a single-sentence, compa…
Interactive Path Reasoning on Graph for Conversational Recommendation
Wenqiang Lei, Gangyi Zhang, Xiangnan He +4
Traditional recommendation systems estimate user preference on items from past interaction history, thus suffering from the limitations of obtaining fine-grained and dynamic user p…
Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
Wenqiang Lei, Xiangnan He, Yisong Miao +4
Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conv…