Presented by
Unify
Build AI Your Way ✨
Hosted By
Token-wise Influential Training Data Retrieval for Large Language Models
Registration
Past Event
About Event
In this session, we welcome Huawei Lin from the Rochester Institute of Technology, who co-authored the paper "Token-wise Influential Training Data Retrieval for Large Language Models".
The paper can be found here.
The paper proposes a scalable framework adapting to LLMs to estimate the influence of
each training data on the LLM output.
Presented by
Unify
Build AI Your Way ✨
Hosted By