# Language-Induced Priors for Domain Adaptation

arXiv: https://arxiv.org/abs/2605.14301 · HTML: https://mlsanity.com/paper/2605.14301/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [Statistical guarantees for the EM algorithm: From population to sample-based analysis](https://mlsanity.com/paper/1408.2156/) (2014)
- [A Survey on Negative Transfer](https://mlsanity.com/paper/2009.00909/) (2020)
- [Domain Aggregation Networks for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1909.05352/) (2019)
- [Probabilistic Medical Predictions of Large Language Models](https://mlsanity.com/paper/2408.11316/) (2024)
- [AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling](https://mlsanity.com/paper/2411.17284/) (2024)
- [Improving Domain Generalization with Domain Relations](https://mlsanity.com/paper/2302.02609/) (2023)
- [LanDA: Language-Guided Multi-Source Domain Adaptation](https://mlsanity.com/paper/2401.14148/) (2024)
- [Federated Data Analytics: A Study on Linear Models](https://mlsanity.com/paper/2206.07786/) (2022)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [Minimizing Negative Transfer of Knowledge in Multivariate Gaussian Processes: A Scalable and Regularized Approach](https://mlsanity.com/paper/1901.11512/) (2019)
- [CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings](https://mlsanity.com/paper/2507.07125/) (2025)

## Abstract (arXiv)

Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant source domains from irrelevant ones, which often leads to negative transfer. In this paper, we address this challenge by leveraging expert textual descriptions of the target domain, a resource that is often available but overlooked. We propose a probabilistic framework that translates these semantic descriptions into a choice model, namely a Language-Induced Prior (LIP), that learns the preferences from a pretrained Large Language Model (LLM). The LIP is then integrated into an Expectation-Maximization algorithm to identify source relevance. Methodologically, this framework is compatible with any parametric model where a likelihood is available. It allows the LIP to guide the selection of sources when target signals are weak, while gradually refining these choices as samples accumulate. Theoretically, we prove that the estimator roughly matches an oracle cold-start MSE under a correct prior, while remaining asymptotically consistent regardless of the quality of the LIP. Empirically, we validated the framework on a descriptive (Gaussian estimation), a predictive (C-MAPSS dataset), and a prescriptive task (MuJoCo hopper).