4 papers
EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval
Huiqi Miao, Xinbao Sun, Bo Wang +6
Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.8% of responses meet all requirements simultaneously, revealin…
ChildEval: When large language models meet children's personalities
Yanyan Luo, Xue Han, Chunxu Zhao +5
While LLMs enable personalized chatbots, their effectiveness in child-centered personalization remains unclear, as systematic evaluation of child-specific preferences is still lack…
Temporal Alignment of LLMs through Cycle Encoding for Long-Range Time Representations
Xue Han, Qian Hu, Yitong Wang +6
Large language models (LLMs) suffer from temporal misalignment issues especially across long span of time. The issue arises from knowing that LLMs are trained on large amounts of d…
Towards Comprehensive Preference Data Collection for Reward Modeling
Yulan Hu, Qingyang Li, Sheng Ouyang +6
Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models (LLMs) with human preferences, thereby enhancing the quality of responses gener…