collaborators

11 papers

cs.AI2026

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-…

cs.CV2026

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…

cs.CL2026

Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation

Peiyang Liu, Qiang Yan, Ziqiang Cui +3

Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-maki…

cs.LG2026

Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization

Rongzheng Wang, Yihong Huang, Muquan Li +6

Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heur…

cs.AI2026

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories

Peiyang Liu, Zhirui Chen, Xi Wang +4

Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain inefficient. Standard approaches ret…

cs.CR2026

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Junchen Li, Chao Qi, Rongzheng Wang +7

Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing a…