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

Chenhan Yuan, Fei Huang, Ru Peng, Keming Lu, Bowen Yu, Chang Zhou, Jingren Zhou


Abstract
Transformer-based large language models (LLMs) exhibit limitations such as generating unsafe responses, unreliable reasoning, etc. Existing inference intervention approaches attempt to mitigate these issues by finetuning additional models to produce calibration signals (such as rewards) that guide the LLM’s decoding process. However, this solution introduces substantial time and space overhead due to the separate models required. This work proposes Non-disruptive parameters insertion (Otter), inserting extra parameters into the transformer architecture to predict calibration signals along with the original LLM output. Otter offers state-of-the-art performance on multiple demanding tasks while saving up to 86.5% extra space and 98.5% extra time. Furthermore, Otter seamlessly integrates with existing inference engines, requiring only a one-line code change, and the original model response remains accessible after the parameter insertion.
Anthology ID:
2024.emnlp-main.316
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5527–5542
Language:
URL:
https://aclanthology.org/2024.emnlp-main.316
DOI:
10.18653/v1/2024.emnlp-main.316
Bibkey:
Cite (ACL):
Chenhan Yuan, Fei Huang, Ru Peng, Keming Lu, Bowen Yu, Chang Zhou, and Jingren Zhou. 2024. Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5527–5542, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model (Yuan et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.316.pdf