2 papers
cs.CL2025
SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems
Kaihong Li, Huichi Zhou, Bin Ma +1
Recommender systems (RS) are widely used in e-commerce for personalized suggestions, yet their openness makes them susceptible to shilling attacks, where adversaries inject fake be…
cs.CL2025
Moral Reasoning Across Languages: The Critical Role of Low-Resource Languages in LLMs
Huichi Zhou, Zehao Xu, Munan Zhao +3
In this paper, we introduce the Multilingual Moral Reasoning Benchmark (MMRB) to evaluate the moral reasoning abilities of large language models (LLMs) across five typologically di…