arXiv：cs.LG· Tailia Malloy, Prateek Kumar Rajput, Serge Lionel Nikiema, Cleotilde Gonzalez, Tegawend\'e F. Bissyand\'e·· 2 天前AI 评分30
基于实例学习理论的能量模型元认知推理框架 MERITED
Metacognitive Reasoning in Energy Based Models using Instance Based Learning Theory
AI 导读
研究者提出 MERITED 框架，将实例学习理论（IBLT）与能量模型（EBM）结合，实现基于不确定性的推理算力动态分配。该工作开源了一个 191M 参数的推理 EBM 权重，并基于 IBL 模型实现了 MERITED 的动态算力分配。EBM 可解释地建模不确定性并动态分配算力，弥补了 LLM 无法在响应前估计不确定性、无法动态分配资源的不足。
正文
Abstract:Metacognition involves reasoning about cognitive processes themselves. An example is in resource allocation where we choose how much time and effort to put into a reasoning task before we begin based on our confidence. Current Artificial Intelligence (AI) systems that rely on Large Language Models (LLMs) cannot estimate their uncertainty about an output without first responding, and cannot dynamically allocate resources to producing an output, making this type of metacognitive process difficult. A recently proposed alternative to classic transformer architectures that addresses these two concerns is the Energy Based Model (EBM) which allows for interpretable uncertainty modeling and dynamic allocation of compute resources. While EBMs can allow for control of these two processes, the actual metacognitive task of determining compute allocation based on uncertainty is not directly addressed. Instance-Based Learning Theory (IBLT) provides an approach to modeling human-like decisions from experience that has previously been applied to predicting human metacognitive reasoning. In this paper we introduce a framework for MEtacognitive Reasoning with Instance-based Learning Theory and Energy Dynamics (MERITED). Grounded in IBLT, this framework allows for control of the computational effort allocated in an EBM to allow for metacognitive control over reasoning effort based on uncertainty while remaining computationally efficient. This work has two main contributions, the training and open weight sharing of a 191M parameter reasoning EBM, and an implementation of the MERITED framework for dynamic compute allocation using an IBL model.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00399 [cs.LG] |
| (or arXiv:2610.00399v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00399 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tailia Malloy [view email]
[v1]
Wed, 30 Sep 2026 12:08:51 UTC (1,041 KB)
来源：arXiv：cs.LG · arxiv.org