arxiv:2506.22809

BayesLoRA: Task-Specific Uncertainty in Low-Rank Adapters

Published on Jun 28

Authors:

Abstract

BayesLoRA combines MC-Dropout with Low-Rank Adapters to provide task-specific uncertainty quantification, enhancing agent decision-making reliability.

AI-generated summary

We propose BayesLoRA, a task-specific uncertainty quantification framework that integrates MC-Dropout into Low-Rank Adapters (LoRA). Unlike general-purpose transformer uncertainty methods, BayesLoRA provides guardrails tailored to downstream workflows, enabling agents to introspect and modulate behavior under uncertainty. We demonstrate mathematically and empirically that LoRA adapters exhibit amplified variance outside fine-tuning distributions, yielding reliable confidence estimates for agentic decision-making.

View arXiv page View PDF Add to collection

Community

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.22809 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.22809 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.22809 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.