18 papers
Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment
Peiyang Liu, Xi Wang, Ziqiang Cui +2
In-context learning (ICL) can induce emergent misalignment (EM), where narrow misaligned examples alter answers to unrelated questions. Existing prompts, however, conflate harmful-…
AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction
Ziqiang Cui, Han Shi, Bowei He +8
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several f…
Progress- and Reliability-Oriented Group Policy Optimization for Agentic Reinforcement Learning
Mingxuan Fan, Peiyang Liu
Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks. To obtain finer-grained policy…
Less Is More: Elevating RAG via Performance-Driven Context Compression
Ziqiang Cui, Yunpeng Weng, Xing Tang +7
Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. Howeve…
Looking Farther with Confidence: Uncertainty-Guided Future Learning for Sequential Recommendation
Ziqiang Cui, Xing Tang, Peiyang Liu +4
Sequential recommendation effectively models dynamic user interests but continues to face challenges related to data sparsity. While self-supervised learning has alleviated this is…
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
Peiyang Liu, Ziqiang Cui, Xi Wang +2
Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external…