Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915855172894720 |
|---|---|
| author | Atinafu, Yonas Lin, Henry Cohen, Robin |
| author_facet | Atinafu, Yonas Lin, Henry Cohen, Robin |
| contents | In this paper, we present a novel black-box online controller that uses only end-to-end measurements over short segments, without internal instrumentation, and hill climbing to maximize goodput, defined as the throughput of requests that satisfy the service-level objective. We provide empirical evidence that this design is well-founded. Using this advance in LLM serving as a concrete example, we then discuss the importance of integrating system performance and sustainability metrics into Factsheets for organizations adopting AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11340 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI Atinafu, Yonas Lin, Henry Cohen, Robin Artificial Intelligence Performance In this paper, we present a novel black-box online controller that uses only end-to-end measurements over short segments, without internal instrumentation, and hill climbing to maximize goodput, defined as the throughput of requests that satisfy the service-level objective. We provide empirical evidence that this design is well-founded. Using this advance in LLM serving as a concrete example, we then discuss the importance of integrating system performance and sustainability metrics into Factsheets for organizations adopting AI systems. |
| title | Improving LLM Performance Through Black-Box Online Tuning: A Case for Adding System Specs to Factsheets for Trusted AI |
| topic | Artificial Intelligence Performance |
| url | https://arxiv.org/abs/2603.11340 |