Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Rai, Daking"'
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:
Rai, Daking, Yao, Ziyu
Large language models (LLMs) have shown strong arithmetic reasoning capabilities when prompted with Chain-of-Thought (CoT) prompts. However, we have only a limited understanding of how they are processed by LLMs. To demystify it, prior work has prima
Externí odkaz:
http://arxiv.org/abs/2406.12288
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
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