Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs
Keywords: trustworthy large language models, Reliable machine learning, tabular data, model multiplicity, high-stakes application
Abstract: Fine-tuning large language models (LLMs) on tabular data for classification can lead to the phenomenon of \emph{fine-tuning multiplicity}, where equally well-performing models make conflicting predictions on the same input. Fine-tuning multiplicity can arise due to variations in the training process, e.g., seed, random weight initialization, retraining on a few additional or deleted data points. This raises critical concerns about the robustness and reliability of Tabular LLMs, particularly when deployed for high-stakes decision-making, such as finance, hiring, education, healthcare, etc. This work formalizes the unique challenge of fine-tuning multiplicity in Tabular LLMs and proposes a novel measure to quantify the robustness of individual predictions without expensive model retraining. Our measure quantifies a prediction's robustness by analyzing (sampling) the model's local behavior around the input in the embedding space. Interestingly, we show that sampling in the local neighborhood can be leveraged to provide probabilistic robustness guarantees against a broad class of equally-well-performing fine-tuned models. By leveraging Bernstein's Inequality, we show that predictions with sufficiently high robustness (as defined by our measure) will remain consistent with high probability. We also provide empirical evaluation on real-world datasets to support our theoretical results. Our work highlights the importance of addressing fine-tuning instabilities to enable trustworthy deployment of Tabular LLMs in high-stakes and safety-critical applications.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
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: 8806
Loading