将大模型遗忘行为视为适应性认知机制，提升长时推理能力。
Forgetting as a Feature: Cognitive Alignment of Large Language Models
- 将大模型推理建模为指数衰减的概率记忆过程。
- 实验证明模型遗忘率与人类记忆效率匹配。
- 提出概率记忆提示法，增强长期推理表现。
大型语言模型（LLMs）常被以完美贝叶斯推断为标准评估，但越来越多证据表明其上下文推理存在系统性遗忘。我们不将此视为缺陷，而是将其重新诠释为功能性认知机制。借鉴人类记忆动态，我们将LLM推理建模为受指数衰减支配的概率记忆过程。引入基准套件，评估时间推理、概念漂移适应和关联回忆，实现模型行为与人类认知模式的直接对比。实证结果表明，LLMs表现出与人类记忆效率权衡相似的遗忘速率。基于此，我们提出概率记忆提示法，一种轻量级策略，通过模拟人类记忆衰减来优化证据整合，显著提升长时推理性能。研究结论表明，遗忘并非故障，而是适应性智能的合理机制。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this behavior as a limitation, we reinterpret forgetting as a functional cognitive mechanism. Drawing inspiration from human memory dynamics, we model LLM inference as a probabilistic memory process governed by exponential decay. We introduce a benchmark suite that evaluates temporal reasoning, concept drift adaptation, and associative recall, enabling direct comparison between model behavior and human cognitive patterns. Our empirical results reveal that LLMs demonstrate forgetting rates analogous to human memory efficiency trade-offs between stability and adaptability. Building on these observations, we propose probabilistic memory prompting, a lightweight strategy that shapes evidence integration to mimic human-like memory decay, leading to improved long-horizon reasoning performance. Our findings position forgetting not as a failure mode, but as a principled mechanism for adaptive intelligence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。