2024/05/20 by Siyu Lou, Lou, Siyu, Yuntian Chen +7 · 1 citation
Business, Management and Accounting · Computer Science · #Artificial Intelligence (cs.AI) #Big Data and Business Intelligence #Business Process Modeling and Analysis #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.2405.11880
openalex publication_date 2024/05/20 · openalex created_date 2024/05/22 · openalex updated_date 2026/07/28
In this study, we propose an axiomatic system to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language generation. These effects are formulated as non-linear interactions between tokens/words encoded by the LLM. Specifically, the axiomatic system enables us to categorize the memorization effects into foundational memorization effects and chaotic memorization effects, and further classify in-context reasoning effects into enhanced inference patterns, eliminated inference patterns, and reversed inference patterns. Besides, the decomposed effects satisfy the sparsity property and the universal matching property, which mathematically guarantee that the LLM's confidence score can be faithfully decomposed into the memorization effects and in-context reasoning effects. Experiments show that the clear disentanglement of memorization effects and in-context reasoning effects enables a straightforward examination of detailed inference patterns encoded by LLMs.