View in EDS HTML Full Text PDF Full Text

Accelerating Inference in Retrieval-Augmented Generation Models for Long-Form Question Answering via Dynamic Token Pruning.

Saved in:
Bibliographic Details
Title: Accelerating Inference in Retrieval-Augmented Generation Models for Long-Form Question Answering via Dynamic Token Pruning.
Authors: Kim, Wooseok1 (AUTHOR), Kim, Gyunyeop1 (AUTHOR), Kang, Sangwoo1 (AUTHOR) swkang@gachon.ac.kr
Source: Mathematics (2227-7390). Jul2025, Vol. 13 Issue 14, p2231. 18p.
Database: Academic Search Ultimate
Full text is not displayed to guests.
Be the first to leave a comment!
You must be logged in first