关注
Vedant Palit
标题
引用次数
引用次数
年份
Towards vision-language mechanistic interpretability: A causal tracing tool for blip
V Palit, R Pandey, A Arora, PP Liang
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
92023
Knowledge graph guided semantic evaluation of language models for user trust
K Roy, T Garg, V Palit
2023 IEEE Conference on Artificial Intelligence (CAI), 234-236, 2023
62023
QA-RAG: Leveraging Question and Answer-based Retrieved Chunk Re-Formatting for Improving Response Quality During Retrieval-augmented Generation
K Roy, Y Zi, C Shyalika, R Prasad, S Murali, V Palit, A Sheth
Preprints, 2024
2024
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Noise-free Text-Image Corruption and Evaluation
M Golovanesky, W Rudman, V Palit, R Singh, C Eickhoff
arXiv preprint arXiv:2406.16320, 2024
2024
WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions
S Mohammadi, E Raff, J Malekar, V Palit, F Ferraro, M Gaur
arXiv preprint arXiv:2406.12058, 2024
2024
系统目前无法执行此操作,请稍后再试。
文章 1–5