# LaMPP: Language Models as Probabilistic Priors for Perception and Action Source: [LaMPP: Language Models as Probabilistic Priors for Perception and Action]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:59:52.182Z Authors: Belinda Z. Li, William Chen, Pratyusha Sharma, Jacob Andreas Published: 2023-02-03T15:14:04.000Z ## Abstract Language models trained on large text corpora encode rich distributional information about real-world environments and action sequences. This information plays a crucial role in current approaches to language processing tasks like question answering and instruction generation. We describe how to leverage language models for \*non-linguistic\* perception and control tasks. Our approach casts labeling and decision-making as inference in probabilistic graphical models in which language models parameterize prior distributions over labels, decisions and parameters, making it possible to integrate uncertain observations and incomplete background knowledge in a principled way. Applied to semantic segmentation, household navigation, and activity recognition tasks, this approach improves predictions on rare, out-of-distribution, and structurally novel inputs. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()