Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.10810 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914258162286592 |
|---|---|
| author | Peng, Mengmeng Fang, Zhenyu Sun, He |
| author_facet | Peng, Mengmeng Fang, Zhenyu Sun, He |
| contents | Large language models (LLMs) currently suffer from parameter entanglement, where general reasoning capabilities (logic) and specific factual knowledge (facts) exist in a superposition state within shared weights. This coupling leads to the "memory wall," where computational capacity is squandered on simulating retrieval, often resulting in hallucinations. In this paper, we propose "digital metabolism," a thermodynamic hypothesis suggesting that targeted forgetting is necessary for distilling a pure neural logic core. To validate this hypothesis, we introduce the Regenerative Logic-Core Protocol (RLCP), a dual-stream training framework that renders specific factual dependencies linearly undecodable via deep-layer gradient reversal. Applying RLCP to Qwen2.5-0.5B, we observe a distinct phase transition: the model achieves near-zero retention of targeted factual associations (Accuracy < 7%) while exhibiting changes consistent with an emergent "structural crystallization" effect. Empirical analysis on GSM8K reveals that the "metabolized" model spontaneously adopts chain-of-thought (CoT) scaffolding, which we interpret as compensating for the loss of direct associative recall (shifting from $O(1)$ recall to $O(N)$ reasoning). While the causal mechanism underlying this behavioral shift requires further investigation, our findings provide a dynamic weight-level counterpart to architectural innovations like DeepSeek's Engram, paving the way for modular "Neural CPU + Symbolic RAM" architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10810 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Digital Metabolism: Decoupling Logic from Facts via Regenerative Unlearning -- Towards a Pure Neural Logic Core Peng, Mengmeng Fang, Zhenyu Sun, He Machine Learning Artificial Intelligence Large language models (LLMs) currently suffer from parameter entanglement, where general reasoning capabilities (logic) and specific factual knowledge (facts) exist in a superposition state within shared weights. This coupling leads to the "memory wall," where computational capacity is squandered on simulating retrieval, often resulting in hallucinations. In this paper, we propose "digital metabolism," a thermodynamic hypothesis suggesting that targeted forgetting is necessary for distilling a pure neural logic core. To validate this hypothesis, we introduce the Regenerative Logic-Core Protocol (RLCP), a dual-stream training framework that renders specific factual dependencies linearly undecodable via deep-layer gradient reversal. Applying RLCP to Qwen2.5-0.5B, we observe a distinct phase transition: the model achieves near-zero retention of targeted factual associations (Accuracy < 7%) while exhibiting changes consistent with an emergent "structural crystallization" effect. Empirical analysis on GSM8K reveals that the "metabolized" model spontaneously adopts chain-of-thought (CoT) scaffolding, which we interpret as compensating for the loss of direct associative recall (shifting from $O(1)$ recall to $O(N)$ reasoning). While the causal mechanism underlying this behavioral shift requires further investigation, our findings provide a dynamic weight-level counterpart to architectural innovations like DeepSeek's Engram, paving the way for modular "Neural CPU + Symbolic RAM" architectures. |
| title | Digital Metabolism: Decoupling Logic from Facts via Regenerative Unlearning -- Towards a Pure Neural Logic Core |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.10810 |