Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lou, Siyu, Chen, Yuntian, Liang, Xiaodan, Lin, Liang, Zhang, Quanshi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913356987760640
author Lou, Siyu
Chen, Yuntian
Liang, Xiaodan
Lin, Liang
Zhang, Quanshi
author_facet Lou, Siyu
Chen, Yuntian
Liang, Xiaodan
Lin, Liang
Zhang, Quanshi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11880
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
Lou, Siyu
Chen, Yuntian
Liang, Xiaodan
Lin, Liang
Zhang, Quanshi
Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
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.
title Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
topic Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11880