The Ability of Large Language Models to Evaluate Constraint-satisfaction in Agent Responses to Open-ended Requests
Keywords: LLM-as-a-Judge, constraint-satisfaction
TL;DR: Benchmarking LLMs on evaluating arithmetic constraint-satisfaction in No One Right Answer scenarios
Abstract: Generative AI agents are often expected to respond to complex user requests that have No One Right Answer (NORA), e.g., "design a vegetarian meal plan below 1800 calories". Such requests may entail a set of constraints that the agent should adhere to. To successfully develop agents for NORA scenarios, an accurate automatic evaluation framework is essential, and specifically - one capable of validating the satisfaction of constraints in the agent's response. Recently, large language models (LLMs) have been adopted as versatile evaluators for many NORA tasks, but their ability to evaluate constraint-satisfaction in generated text remains unclear. To study this, we develop and release a novel Arithmetic Constraint-Satisfaction (ACS) benchmarking dataset. The dataset consists of complex user requests with corresponding constraints, agent responses and human labels indicating each constraint's satisfaction level in the response. A unique property of this dataset is that validating many of its constraints requires reviewing the response as a whole (in contrast to many other benchmarks that require the validation of a single independent item). Moreover, it assesses LLMs in performing reasoning, in-context data extraction, arithmetic calculations, and counting. We then benchmark both open and proprietary LLMs on evaluating constraint-satisfaction, and show that most models still have a significant headroom for improvement, and that errors primarily stem from reasoning issues. In addition, most models exhibit a skewed constraint-satisfaction prediction pattern, with higher accuracy where the ground-truth label is "satisfied". Lastly, few-shot prompting for our task proved to be rather challenging, since many of the studied models showed a degradation in performance when it was introduced.
Primary Area: datasets and benchmarks
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.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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: 2514
Loading