Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916844471844864 |
|---|---|
| author | Sikka, Varin Sikka, Vishal |
| author_facet | Sikka, Varin Sikka, Vishal |
| contents | In this paper we explore hallucinations and related capability limitations in LLMs and LLM-based agents from the perspective of computational complexity. We show that beyond a certain complexity, LLMs are incapable of carrying out computational and agentic tasks or verifying their accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07505 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models Sikka, Varin Sikka, Vishal Computation and Language Artificial Intelligence In this paper we explore hallucinations and related capability limitations in LLMs and LLM-based agents from the perspective of computational complexity. We show that beyond a certain complexity, LLMs are incapable of carrying out computational and agentic tasks or verifying their accuracy. |
| title | Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.07505 |