Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection

no code implementations • 15 Apr 2024 • Yuxi Li, Yi Liu, Gelei Deng, Ying Zhang, Wenjia Song, Ling Shi, Kailong Wang, Yuekang Li, Yang Liu, Haoyu Wang

We present categorizations of the identified glitch tokens and symptoms exhibited by LLMs when interacting with glitch tokens.

Embedding Code Contexts for Cryptographic API Suggestion:New Methodologies and Comparisons

no code implementations • 15 Mar 2021 • Ya Xiao, Salman Ahmed, Wenjia Song, Xinyang Ge, Bimal Viswanath, Danfeng Yao

Despite recent research efforts, the vision of automatic code generation through API recommendation has not been realized.

Code Generation