Zobrazeno 1 - 10
of 303
pro vyhledávání: '"Zhou, Yilun"'
Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for interpreting transfor
Externí odkaz:
http://arxiv.org/abs/2407.02646
Autor:
Murthy, Rithesh, Yang, Liangwei, Tan, Juntao, Awalgaonkar, Tulika Manoj, Zhou, Yilun, Heinecke, Shelby, Desai, Sachin, Wu, Jason, Xu, Ran, Tan, Sarah, Zhang, Jianguo, Liu, Zhiwei, Kokane, Shirley, Liu, Zuxin, Zhu, Ming, Wang, Huan, Xiong, Caiming, Savarese, Silvio
The deployment of Large Language Models (LLMs) and Large Multimodal Models (LMMs) on mobile devices has gained significant attention due to the benefits of enhanced privacy, stability, and personalization. However, the hardware constraints of mobile
Externí odkaz:
http://arxiv.org/abs/2406.10290
Recent large language models (LLMs) have shown indications of mathematical reasoning ability on challenging competition-level problems, especially with self-generated verbalizations of intermediate reasoning steps (i.e., chain-of-thought prompting).
Externí odkaz:
http://arxiv.org/abs/2401.06961
One of the motivations for explainable AI is to allow humans to make better and more informed decisions regarding the use and deployment of AI models. But careful evaluations are needed to assess whether this expectation has been fulfilled. Current e
Externí odkaz:
http://arxiv.org/abs/2312.06032
Large language models (LLMs) such as ChatGPT have demonstrated superior performance on a variety of natural language processing (NLP) tasks including sentiment analysis, mathematical reasoning and summarization. Furthermore, since these models are in
Externí odkaz:
http://arxiv.org/abs/2310.11207
Autor:
Zhou, Yilun
The last decade witnessed immense progress in machine learning, which has been deployed in many domains such as healthcare, finance and justice. However, recent advances are largely powered by deep neural networks, whose opacity hinders people's abil
Externí odkaz:
https://hdl.handle.net/1721.1/150171
Compositional and domain generalization present significant challenges in semantic parsing, even for state-of-the-art semantic parsers based on pre-trained language models (LMs). In this study, we empirically investigate improving an LM's generalizat
Externí odkaz:
http://arxiv.org/abs/2305.17378
Autor:
Zhou, Yilun
Counterfactual (CF) explanations, also known as contrastive explanations and algorithmic recourses, are popular for explaining machine learning models in high-stakes domains. For a subject that receives a negative model prediction (e.g., mortgage app
Externí odkaz:
http://arxiv.org/abs/2303.11111
While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success. Our work studies different methods for e
Externí odkaz:
http://arxiv.org/abs/2301.13820
Autor:
Zhou, Yilun, Shah, Julie
Feature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency. In this paper, we highlight an intriguing property of these metrics: their solvabili
Externí odkaz:
http://arxiv.org/abs/2205.08696