Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.07334 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917132687638528 |
|---|---|
| author | Xi, Wang Shi, Quan Ding, Zenghui Gao, Jianqing Yang, Xianjun |
| author_facet | Xi, Wang Shi, Quan Ding, Zenghui Gao, Jianqing Yang, Xianjun |
| contents | The illusion phenomenon of large language models (LLMs) is the core obstacle to their reliable deployment. This article formalizes the large language model as a probabilistic Turing machine by constructing a "computational necessity hierarchy", and for the first time proves the illusions are inevitable on diagonalization, incomputability, and information theory boundaries supported by the new "learner pump lemma". However, we propose two "escape routes": one is to model Retrieval Enhanced Generations (RAGs) as oracle machines, proving their absolute escape through "computational jumps", providing the first formal theory for the effectiveness of RAGs; The second is to formalize continuous learning as an "internalized oracle" mechanism and implement this path through a novel neural game theory framework. Finally, this article proposes a feasible new principle for artificial intelligence security - Computational Class Alignment (CCA), which requires strict matching between task complexity and the actual computing power of the system, providing theoretical support for the secure application of artificial intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07334 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape Xi, Wang Shi, Quan Ding, Zenghui Gao, Jianqing Yang, Xianjun Artificial Intelligence The illusion phenomenon of large language models (LLMs) is the core obstacle to their reliable deployment. This article formalizes the large language model as a probabilistic Turing machine by constructing a "computational necessity hierarchy", and for the first time proves the illusions are inevitable on diagonalization, incomputability, and information theory boundaries supported by the new "learner pump lemma". However, we propose two "escape routes": one is to model Retrieval Enhanced Generations (RAGs) as oracle machines, proving their absolute escape through "computational jumps", providing the first formal theory for the effectiveness of RAGs; The second is to formalize continuous learning as an "internalized oracle" mechanism and implement this path through a novel neural game theory framework. Finally, this article proposes a feasible new principle for artificial intelligence security - Computational Class Alignment (CCA), which requires strict matching between task complexity and the actual computing power of the system, providing theoretical support for the secure application of artificial intelligence. |
| title | Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.07334 |