Let’s Think Var-by-Var: Large Language Models Enable Ad Hoc Probabilistic Reasoning
Keywords: Large Language Models; Ad hoc Probabilisitic Models; Commonsense Reasoning
Abstract: A hallmark of intelligence is the ability to flesh out underspecified situations using “common sense.” We propose to extract that common sense from large language models (LLMs), in a form that can feed into probabilistic inference. We focus our investigation on guesstimation questions such as “How much are Airbnb listings in Newark, NJ?” Formulating a sensible answer without access to data requires drawing on, and integrating, bits of common knowledge about how Price and Location may relate to other variables, such as Property Type. Our framework answers such a question by synthesizing an ad hoc probabilistic model. First we prompt an LLM to propose a set of random variables relevant to the question, followed by moment constraints on their joint distribution. We then optimize the joint distribution p within a log-linear family to maximize the overall constraint satisfaction. Our experiments show that LLMs can successfully be prompted to propose reasonable variables, and while the proposed numerical constraints can be noisy, jointly optimizing for their satisfaction reconciles them. When evaluated on probabilistic questions derived from three real-world tabular datasets, we find that our framework performs comparably to a direct prompting baseline in terms of total variation distance from the dataset distribution, and is similarly robust to noise.
Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)
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: 12600
Loading