LLMs show human-like forgetting rates that can be harnessed through probabilistic memory prompting to improve long-horizon reasoning.
Yet, despite their impressive capabilities, recent studies suggest that LLMs do not operate as ideal Bayesian reasoners with perfect memory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Forgetting as a Feature: Cognitive Alignment of Large Language Models
LLMs show human-like forgetting rates that can be harnessed through probabilistic memory prompting to improve long-horizon reasoning.