17 papers
LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty
Zipeng Ling, Shuliang Liu, Yuehao Tang +7
Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misused: in real-world applications,…
Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis
Zipeng Ling, Shuliang Liu, Shenghong Fu +4
LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinking), which vary by sa…
Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation
Sihang Jia, Shuliang Liu, Songbo Yang +3
Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigat…
PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints
Jiahao Huo, Shuliang Liu, Bin Wang +5
Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing attacks by treating the sentence as…
RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection
Yiming Huang, Junyan Zhang, Zihao Wang +5
Large Language Models (LLMs) have become powerful, but hallucinations remain a vital obstacle to their trustworthy use. Previous works improved the capability of hallucination dete…
A Visual Semantic Adaptive Watermark grounded by Prefix-Tuning for Large Vision-Language Model
Qi Zheng, Shuliang Liu, Yu Huang +8
Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in Large Vision-Language Models (LVLMs). However, vision-agnostic water…