Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model
Paper
•
2408.10764
•
Published
•
8
Keming Lu
keminglu
AI & ML interests
Information Extraction, Large Language Model, Knowledge Graph
Recent Activity
authored
a paper
about 1 month ago
Aligning Large Language Models via Self-Steering Optimization
authored
a paper
about 1 month ago
A Unified View of Delta Parameter Editing in Post-Trained Large-Scale
Models
Organizations
