Predicting the Performance of Black-box LLMs through Follow-up Queries
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_ | 1866912736975257600 |
|---|---|
| author | Sam, Dylan Finzi, Marc Kolter, J. Zico |
| author_facet | Sam, Dylan Finzi, Marc Kolter, J. Zico |
| contents | Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language models are offered only through closed-source APIs, providing only black-box access. In this paper, we predict the behavior of black-box language models by asking follow-up questions and taking the probabilities of responses \emph{as} representations to train reliable predictors. We first demonstrate that training a linear model on these responses reliably and accurately predicts model correctness on question-answering and reasoning benchmarks. Surprisingly, this can \textit{even outperform white-box linear predictors} that operate over model internals or activations. Furthermore, we demonstrate that these follow-up question responses can reliably distinguish between a clean version of an LLM and one that has been adversarially influenced via a system prompt to answer questions incorrectly or to introduce bugs into generated code. Finally, we show that they can also be used to differentiate between black-box LLMs, enabling the detection of misrepresented models provided through an API. Overall, our work shows promise in monitoring black-box language model behavior, supporting their deployment in larger, autonomous systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Predicting the Performance of Black-box LLMs through Follow-up Queries Sam, Dylan Finzi, Marc Kolter, J. Zico Machine Learning Computation and Language Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language models are offered only through closed-source APIs, providing only black-box access. In this paper, we predict the behavior of black-box language models by asking follow-up questions and taking the probabilities of responses \emph{as} representations to train reliable predictors. We first demonstrate that training a linear model on these responses reliably and accurately predicts model correctness on question-answering and reasoning benchmarks. Surprisingly, this can \textit{even outperform white-box linear predictors} that operate over model internals or activations. Furthermore, we demonstrate that these follow-up question responses can reliably distinguish between a clean version of an LLM and one that has been adversarially influenced via a system prompt to answer questions incorrectly or to introduce bugs into generated code. Finally, we show that they can also be used to differentiate between black-box LLMs, enabling the detection of misrepresented models provided through an API. Overall, our work shows promise in monitoring black-box language model behavior, supporting their deployment in larger, autonomous systems. |
| title | Predicting the Performance of Black-box LLMs through Follow-up Queries |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2501.01558 |