Schema for In-Context Learning
By: Pan Chen , Shaohong Chen , Mark Wang and more
Potential Business Impact:
Teaches computers to learn like humans.
In-Context Learning (ICL) enables transformer-based language models to adapt to new tasks by conditioning on demonstration examples. However, traditional example-driven in-context learning lacks explicit modules for knowledge retrieval and transfer at the abstraction level. Inspired by cognitive science, specifically schema theory, which holds that humans interpret new information by activating pre-existing mental frameworks (schemas) to structure understanding, we introduce SCHEMA ACTIVATED IN CONTEXT LEARNING (SA-ICL). This framework extracts the representation of the building blocks of cognition for the reasoning process instilled from prior examples, creating an abstracted schema, a lightweight, structured template of key inferential steps and their relationships, which is then used to augment a model's reasoning process when presented with a novel question. We demonstrate that a broad range of large language models (LLMs) lack the capacity to form and utilize internal schema-based learning representations implicitly, but instead benefit significantly from explicit schema-based scaffolding. Across chemistry and physics questions from the GPQA dataset, our experiments show that SA-ICL consistently boosts performance, up to 36.19 percent, when the single demonstration example is of high quality, which simultaneously reduces reliance on the number of demonstrations and enhances interpretability. SCHEMA ACTIVATED IN CONTEXT LEARNING not only bridges disparate ICL strategies ranging from pattern priming to Chain-of-Thought prompting, but also paves a new path for enhancing human-like reasoning in LLMs.
Similar Papers
A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
Artificial Intelligence
Teaches computers to learn new things from examples.
Is In-Context Learning Learning?
Computation and Language
Computers learn new things from examples, not just memorizing.
Scaling Laws and In-Context Learning: A Unified Theoretical Framework
Machine Learning (CS)
Makes AI learn new things faster with more data.