Intrinsic Barriers to Explaining Deep Foundation Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913806468251648 |
|---|---|
| author | Tan, Zhen Liu, Huan |
| author_facet | Tan, Zhen Liu, Huan |
| contents | Deep Foundation Models (DFMs) offer unprecedented capabilities but their increasing complexity presents profound challenges to understanding their internal workings-a critical need for ensuring trust, safety, and accountability. As we grapple with explaining these systems, a fundamental question emerges: Are the difficulties we face merely temporary hurdles, awaiting more sophisticated analytical techniques, or do they stem from \emph{intrinsic barriers} deeply rooted in the nature of these large-scale models themselves? This paper delves into this critical question by examining the fundamental characteristics of DFMs and scrutinizing the limitations encountered by current explainability methods when confronted with this inherent challenge. We probe the feasibility of achieving satisfactory explanations and consider the implications for how we must approach the verification and governance of these powerful technologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16948 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Intrinsic Barriers to Explaining Deep Foundation Models Tan, Zhen Liu, Huan Computers and Society Artificial Intelligence Emerging Technologies Deep Foundation Models (DFMs) offer unprecedented capabilities but their increasing complexity presents profound challenges to understanding their internal workings-a critical need for ensuring trust, safety, and accountability. As we grapple with explaining these systems, a fundamental question emerges: Are the difficulties we face merely temporary hurdles, awaiting more sophisticated analytical techniques, or do they stem from \emph{intrinsic barriers} deeply rooted in the nature of these large-scale models themselves? This paper delves into this critical question by examining the fundamental characteristics of DFMs and scrutinizing the limitations encountered by current explainability methods when confronted with this inherent challenge. We probe the feasibility of achieving satisfactory explanations and consider the implications for how we must approach the verification and governance of these powerful technologies. |
| title | Intrinsic Barriers to Explaining Deep Foundation Models |
| topic | Computers and Society Artificial Intelligence Emerging Technologies |
| url | https://arxiv.org/abs/2504.16948 |