With the rapid development of large language models (LLMs), role-playing dialogue systems have become increasingly popular for immersive and personalized human–AI interaction. However, in real-world role-playing scenarios, users often provide lazy queries—brief and ambiguous responses such as “oh,” “hmm,” or “?”—which lack explicit intent and emotional cues, making it difficult for role-playing LLMs to generate engaging replies. Existing query rewriting methods mainly target functional tasks such as information retrieval and are not tailored to role-playing dialogue, where rewrite quality depends on role-playing-specific factors such as character consistency and personalized user preferences. To address this, we first propose a listwise Generative Reward Model (GRM) trained from real user preference data collected through online regeneration behavior, which provides fine-grained process and final preference signals for training a Lazy Query Rewriter. Using rejection fine-tuning and reinforcement learning, the LQ-Rewriter learns to transform underspecified user inputs into richer expressions while preserving user intent and dialogue context. Experiments on real-world dialogue logs from a mainstream Chinese AI-powered romantic role-playing platform show that our GRM substantially outperforms general-purpose LLM judges. Moreover, our LQ-Rewriter achieves the highest GRM-based and human preference win rates among all rewriting baselines, and brings tangible improvements in online deployment.

BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a major blocking issue of applying BERT to online services is that it is memory-intensive and leads to unsatisfactory latency of user requests, raising the necessity of model compression. Existing solutions leverage the knowledge distillation framework to learn a smaller model that imitates the behaviors of BERT. However, the training procedure of knowledge distillation is expensive itself as it requires sufficient training data to imitate the teacher model. In this paper, we address this issue by proposing a tailored solution named LadaBERT (Lightweight adaptation of BERT through hybrid model compression), which combines the advantages of different model compression methods, including weight pruning, matrix factorization and knowledge distillation. LadaBERT achieves state-of-the-art accuracy on various public datasets while the training overheads can be reduced by an order of magnitude.