Context Learning
In-context learning (ICL) is a paradigm shift in machine learning, focusing on enabling models to adapt to new tasks using only a few examples provided within the input, without requiring parameter updates. Current research emphasizes understanding ICL's mechanisms, particularly within transformer-based large language models, and improving its effectiveness through techniques like enhanced example selection, chain-of-thought prompting, and addressing issues such as spurious correlations and copy bias. This research is significant because ICL offers a more efficient and adaptable approach to many machine learning problems, impacting fields ranging from natural language processing and computer vision to scientific computing and beyond.
Papers
Fair In-Context Learning via Latent Concept Variables
Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu, Chen Zhao, Feng Chen, Xintao Wu
TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric Videos
Leonardo Plini, Luca Scofano, Edoardo De Matteis, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, Andrea Sanchietti, Giovanni Maria Farinella, Fabio Galasso, Antonino Furnari
Pretrained transformer efficiently learns low-dimensional target functions in-context
Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, Hau-San Wong
Shortcut Learning in In-Context Learning: A Survey
Rui Song, Yingji Li, Lida Shi, Fausto Giunchiglia, Hao Xu
N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs
Ilya Zisman, Alexander Nikulin, Andrei Polubarov, Nikita Lyubaykin, Vladislav Kurenkov
RuAG: Learned-rule-augmented Generation for Large Language Models
Yudi Zhang, Pei Xiao, Lu Wang, Chaoyun Zhang, Meng Fang, Yali Du, Yevgeniy Puzyrev, Randolph Yao, Si Qin, Qingwei Lin, Mykola Pechenizkiy, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
DemoCraft: Using In-Context Learning to Improve Code Generation in Large Language Models
Nirmal Joshua Kapu, Mihit Sreejith
EMOTION: Expressive Motion Sequence Generation for Humanoid Robots with In-Context Learning
Peide Huang, Yuhan Hu, Nataliya Nechyporenko, Daehwa Kim, Walter Talbott, Jian Zhang
Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning
Dong Shu, Mengnan Du
Toward Understanding In-context vs. In-weight Learning
Bryan Chan, Xinyi Chen, András György, Dale Schuurmans