Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model Chenhan Yuan author Fei Huang author Ru Peng author Keming Lu author Bowen Yu author Chang Zhou author Jingren Zhou author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication yuan-etal-2024-predicting 10.18653/v1/2024.emnlp-main.316 https://aclanthology.org/2024.emnlp-main.316/ 2024-11 5527 5542