AutoBencher: Towards Declarative Benchmark Construction

Xiang Lisa Li, Farzaan Kaiyom, Evan Zheran Liu, Yifan Mai, Percy Liang, Tatsunori Hashimoto

Keywords: automatic evaluation, language models

TL;DR: We present AutoBencher, a declarative approach to constructing new datasets, revealing model weakness and safety vulnerabilities.

Abstract: We present AutoBencher, a declarative framework for automatic benchmark construction, and use it to scalably discover novel insights and vulnerabilities of existing language models. Concretely, given a few desiderata of benchmarks (e.g., question difficulty, topic salience), we operationalize each desideratum and cast benchmark creation as an optimization problem. Specifically, we experiment with two settings with different optimization objectives: (i) for capability evaluation, we declare the goal of finding a salient, difficult dataset that induces novel performance patterns; (ii) for safety evaluation, we declare the goal of finding a dataset of unsafe prompts that existing LMs fail to decline. To tackle this optimization problem, we use a language model to iteratively propose and refine dataset descriptions, which are then used to generate topic-specific questions and answers. These descriptions are optimized to improve the declared desiderata. We use AutoBencher (powered by GPT-4) to create datasets for math, multilinguality, knowledge, and safety. The scalability of AutoBencher allows it to test fine-grained categories and tail knowledge, creating datasets that elicit 22% more model errors (i.e., difficulty) than existing benchmarks. On the novelty ends, AutoBencher also helps identify specific gaps not captured by existing benchmarks: e.g., Gemini-Pro has knowledge gaps on Permian Extinction and Fordism while GPT-4o fails to decline harmful requests about cryptocurrency scams.

Primary Area: foundation or frontier models, including LLMs

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9619