2 papers
cs.CL2024
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models
Zhengxuan Wu, Yuhao Zhang, Peng Qi +6
Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between…
cs.IR2023
Personalized Search Via Neural Contextual Semantic Relevance Ranking
Deguang Kong, Daniel Zhou, Zhiheng Huang +1
Existing neural relevance models do not give enough consideration for query and item context information which diversifies the search results to adapt for personal preference. To b…