3 papers
cs.CL2026
OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination
Huiqiang Rong, Haoran Luo, Hui Feng +4
Omni-modal large language models (OmniLLMs) unify text, images, audio, and video, yet hallucinate when generation relies on the wrong evidence. Existing inference-time methods can…
cs.CL2026
CogEvol: Towards Efficient and Reliable Learning Environment Generation
Shangqing Tu, Daniel Zhang-Li, Yucheng Wang +20
We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artifact (structured-JSON slides or…
cs.CL2026
Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
Yifan Zhu, Huiqiang Rong, Haoran Luo
Large Language Models (LLMs) often hallucinate, generating content inconsistent with the input. Retrieval-Augmented Generation (RAG) and Reinforcement Learning with Human Feedback…