Iterative Forward Tuning Boosts In-Context Learning in Language Models

Jiaxi Yang, Binyuan Hui, Min Yang, Bailin Wang, Bowen Li, Binhua Li, Fei Huang, Yongbin Li


Abstract
Despite the advancements in in-context learning (ICL) for large language models (LLMs), current research centers on specific prompt engineering, such as demonstration selection, with the expectation that a single iteration of demonstrations processing can generalize effectively to a given test sample. However, this perspective overlooks the potential benefits derived from multiple iterations involving demonstrations, a practice aligning more closely with the iterative decision-making process exhibited by humans, who often learn through analogy. In this study, we introduce a novel two-stage framework to boost ICL in LLMs. Specifically, our framework delineates the ICL process into two distinct stages: Deep-Thinking and test stages. The Deep-Thinking stage incorporates a unique attention mechanism, i.e., iterative enhanced attention, which enables multiple rounds of information accumulation. This mechanism operates by manipulating the Key-Value matrices without training, fostering enhanced understanding capabilities in LLMs by thinking demonstrations multiple times. We evaluated Deep-Thinking across a range of benchmarks and LLMs, showing its superior performance over vanilla ICL methods and its effectiveness in challenging tasks where demonstration selection is infeasible.
Anthology ID:
2024.acl-long.825
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15460–15473
Language:
URL:
https://aclanthology.org/2024.acl-long.825
DOI:
10.18653/v1/2024.acl-long.825
Bibkey:
Cite (ACL):
Jiaxi Yang, Binyuan Hui, Min Yang, Bailin Wang, Bowen Li, Binhua Li, Fei Huang, and Yongbin Li. 2024. Iterative Forward Tuning Boosts In-Context Learning in Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15460–15473, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Iterative Forward Tuning Boosts In-Context Learning in Language Models (Yang et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.825.pdf