BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning
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_ | 1866916877058441216 |
|---|---|
| author | Zhou, Jinan Ghosh, Rajat Bhargava, Vaishnavi Dutta, Debojyoti Singhal, Aryan |
| author_facet | Zhou, Jinan Ghosh, Rajat Bhargava, Vaishnavi Dutta, Debojyoti Singhal, Aryan |
| contents | When designing LLM services, practitioners care about three key properties: inference-time budget, factual authenticity, and reasoning capacity. However, our analysis shows that no model can simultaneously optimize for all three. We formally prove this trade-off and propose a principled framework named The BAR Theorem for LLM-application design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning Zhou, Jinan Ghosh, Rajat Bhargava, Vaishnavi Dutta, Debojyoti Singhal, Aryan Machine Learning When designing LLM services, practitioners care about three key properties: inference-time budget, factual authenticity, and reasoning capacity. However, our analysis shows that no model can simultaneously optimize for all three. We formally prove this trade-off and propose a principled framework named The BAR Theorem for LLM-application design. |
| title | BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.23170 |