8 citations · 13 across the 11 of their papers we have counts for
12 papers
VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
Seongheon Park, Changdae Oh, Hyeong Kyu Choi +2
Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's abili…
Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis
Leitian Tao, Xuefeng Du, Sharon Li
Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesi…
Foundations of Unknown-aware Machine Learning
Xuefeng Du
Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical f…
Steer LLM Latents for Hallucination Detection
Seongheon Park, Xuefeng Du, Min-Hsuan Yeh +2
Hallucinations in LLMs pose a significant concern to their safe deployment in real-world applications. Recent approaches have leveraged the latent space of LLMs for hallucination d…
Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
Changdae Oh, Zhen Fang, Shawn Im +2
Multimodal large language models (MLLMs) have shown promising capabilities but struggle under distribution shifts, where evaluation data differ from instruction tuning distribution…
Safety-Aware Fine-Tuning of Large Language Models
Hyeong Kyu Choi, Xuefeng Du, Yixuan Li
Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be di…
Challenges and Future Directions of Data-Centric AI Alignment
Min-Hsuan Yeh, Jeffrey Wang, Xuefeng Du +4
As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignmen…
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
Xuefeng Du, Chaowei Xiao, Yixuan Li
The surge in applications of large language models (LLMs) has prompted concerns about the generation of misleading or fabricated information, known as hallucinations. Therefore, de…
Out-of-Distribution Learning with Human Feedback
Haoyue Bai, Xuefeng Du, Katie Rainey +2
Out-of-distribution (OOD) learning often relies heavily on statistical approaches or predefined assumptions about OOD data distributions, hindering their efficacy in addressing mul…
When and How Does In-Distribution Label Help Out-of-Distribution Detection?
Xuefeng Du, Yiyou Sun, Yixuan Li
Detecting data points deviating from the training distribution is pivotal for ensuring reliable machine learning. Extensive research has been dedicated to the challenge, spanning c…
How Does Unlabeled Data Provably Help Out-of-Distribution Detection?
Xuefeng Du, Zhen Fang, Ilias Diakonikolas +1
Using unlabeled data to regularize the machine learning models has demonstrated promise for improving safety and reliability in detecting out-of-distribution (OOD) data. Harnessing…
Dream the Impossible: Outlier Imagination with Diffusion Models
Xuefeng Du, Yiyou Sun, Xiaojin Zhu +1
Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor…