# LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers

arXiv: https://arxiv.org/abs/2506.00998 · HTML: https://mlsanity.com/paper/2506.00998/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 12 of 12)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [VOS: Learning What You Don't Know by Virtual Outlier Synthesis](https://mlsanity.com/paper/2202.01197/) (2022)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement](https://mlsanity.com/paper/2310.00227/) (2023)
- [Detection of out-of-distribution samples using binary neuron activation patterns](https://mlsanity.com/paper/2212.14268/) (2022)
- [BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection](https://mlsanity.com/paper/2403.18373/) (2024)
- [Out-of-Distribution Detection with Prototypical Outlier Proxy](https://mlsanity.com/paper/2412.16884/) (2024)

## Abstract (arXiv)

Fine-tuning large language models (LLMs) improves performance on domain-specific tasks but can lead to overfitting, making them unreliable on out-of-distribution (OoD) queries. We propose LoRA-BAM - a method that adds OoD detection monitors to the LoRA layer using boxed abstraction to filter questions beyond the model's competence. Feature vectors from the fine-tuning data are extracted via the LLM and clustered. Clusters are enclosed in boxes; a question is flagged as OoD if its feature vector falls outside all boxes. To improve interpretability and robustness, we introduce a regularization loss during fine-tuning that encourages paraphrased questions to stay close in the feature space, and the enlargement of the decision boundary is based on the feature variance within a cluster. Our method complements existing defenses by providing lightweight and interpretable OoD detection.