7 papers
Forged Peer Judgments Mislead Multimodal LLM Judge Panels: Source-Blind Anchoring and Panel-Consensus Verification
Yang Shu
Multimodal LLM judge panels can cross-reference peers, but a quoted peer judgment may itself be untrusted. We expose source-blind anchoring as a text-level attack surface in vision…
Faster but Different: Diagnosing and Controlling Content Drift in Accelerated Multimodal Diffusion Language Models
Yaoxuan Dou, Yang Shu
Training-free acceleration makes diffusion-based multimodal large language models (dMLLMs) more deployable, but it may silently change generated content. We study this serving-time…
Agentic Retrieval-Augmented Generation for Financial Document Question Answering
Yang Shu, Yingmin Liu, Zequn Xie
Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and footnotes--scatter…
Numbers Beat Words: A Rigorous On-Premise Benchmark for Coupled MIMO Controller Tuning
Jiaxuan Chen, Haonan Li, Yang Shu
Tuning controllers for strongly coupled multi-input multi-output (MIMO) processes is difficult because decentralized auto-tuning ignores loop interaction and local optimization is…
ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation
Chenyu Wang, Yueyuan Li, Yingmin Liu +1
Retrieval-Augmented Generation (RAG) systems implicitly assume mutual consistency among retrieved documents -- an assumption that frequently fails in practice. We present ConflictR…
CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models
Yuning Wu, Yingmin Liu, Yang Shu
Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please recons…