Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs

• URL: http://arxiv.org/abs/2509.04655v2
• Date: Mon, 15 Sep 2025 19:42:21 GMT
• Title: Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
• Authors: Ayush Gupta, Ramneet Kaur, Anirban Roy, Adam D. Cobb, Rama Chellappa, Susmit Jha,
• Abstract summary: We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs)<n>Motivated by recent findings on polysemanticity and redundancy in LLMs, we hypothesize that in-domain inputs exhibit higher dropout tolerance than OOD inputs.<n>We aggregate dropout tolerance across multiple layers via a valid ensemble approach, improving detection while maintaining theoretical false alarm bounds from ICAD.
• Score: 35.326974180503065
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain tasks through fine-tuning, specialized LLMs remain vulnerable to incorrect or unreliable outputs when presented with OOD inputs, posing risks in critical applications. Our method leverages the Inductive Conformal Anomaly Detection (ICAD) framework, using a new non-conformity measure based on the model's dropout tolerance. Motivated by recent findings on polysemanticity and redundancy in LLMs, we hypothesize that in-domain inputs exhibit higher dropout tolerance than OOD inputs. We aggregate dropout tolerance across multiple layers via a valid ensemble approach, improving detection while maintaining theoretical false alarm bounds from ICAD. Experiments with medical-specialized LLMs show that our approach detects OOD inputs better than baseline methods, with AUROC improvements of $2\%$ to $37\%$ when treating OOD datapoints as positives and in-domain test datapoints as negatives.

Related papers

• Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection [15.184096796229115]
  We propose a post-hoc method, Perturbation-Rectified OOD detection (PRO), based on the insight that prediction confidence for OOD inputs is more susceptible to reduction under perturbation than in-distribution (IND) inputs.<n>On a CIFAR-10 model with adversarial training, PRO effectively detects near-OOD inputs, achieving a reduction of more than 10% on FPR@95 compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-24T15:32:33Z)
• DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection [11.332987462182713]
  In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics.<n>We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder framework that harnesses this mechanism.<n>DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks.
  arXiv  Detail & Related papers  (2025-01-14T10:49:26Z)
• Margin-bounded Confidence Scores for Out-of-Distribution Detection [2.373572816573706]
  We propose a novel method called Margin bounded Confidence Scores (MaCS) to address the nontrivial OOD detection problem. MaCS enlarges the disparity between ID and OOD scores, which in turn makes the decision boundary more compact. Experiments on various benchmark datasets for image classification tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-09-22T05:40:25Z)
• Model-free Test Time Adaptation for Out-Of-Distribution Detection [62.49795078366206]
  We propose a Non-Parametric Test Time textbfAdaptation framework for textbfDistribution textbfDetection (abbr) abbr utilizes online test samples for model adaptation during testing, enhancing adaptability to changing data distributions. We demonstrate the effectiveness of abbr through comprehensive experiments on multiple OOD detection benchmarks.
  arXiv  Detail & Related papers  (2023-11-28T02:00:47Z)
• How Good Are LLMs at Out-of-Distribution Detection? [13.35571704613836]
  Out-of-distribution (OOD) detection plays a vital role in enhancing the reliability of machine learning (ML) models. This paper embarks on a pioneering empirical investigation of OOD detection in the domain of large language models (LLMs)
  arXiv  Detail & Related papers  (2023-08-20T13:15:18Z)
• Beyond AUROC & co. for evaluating out-of-distribution detection performance [50.88341818412508]
  Given their relevance for safe(r) AI, it is important to examine whether the basis for comparing OOD detection methods is consistent with practical needs. We propose a new metric - Area Under the Threshold Curve (AUTC), which explicitly penalizes poor separation between ID and OOD samples.
  arXiv  Detail & Related papers  (2023-06-26T12:51:32Z)
• Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations [111.88727295707454]
  This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We propose a benchmark construction protocol that ensures clear differentiation and challenging distribution shifts. We conduct experiments on pre-trained language models for analysis and evaluation of OOD robustness.
  arXiv  Detail & Related papers  (2023-06-07T17:47:03Z)
• AUTO: Adaptive Outlier Optimization for Test-Time OOD Detection [79.51071170042972]
  Out-of-distribution (OOD) detection aims to detect test samples that do not fall into any training in-distribution (ID) classes.<n>Data safety and privacy make it infeasible to collect task-specific outliers in advance for different scenarios.<n>We present test-time OOD detection, which allows the deployed model to utilize real OOD data from the unlabeled data stream during testing.
  arXiv  Detail & Related papers  (2023-03-22T02:28:54Z)
• Learn what you can't learn: Regularized Ensembles for Transductive Out-of-distribution Detection [76.39067237772286]
  We show that current out-of-distribution (OOD) detection algorithms for neural networks produce unsatisfactory results in a variety of OOD detection scenarios. This paper studies how such "hard" OOD scenarios can benefit from adjusting the detection method after observing a batch of the test data. We propose a novel method that uses an artificial labeling scheme for the test data and regularization to obtain ensembles of models that produce contradictory predictions only on the OOD samples in a test batch.
  arXiv  Detail & Related papers  (2020-12-10T16:55:13Z)
• Robust Out-of-distribution Detection for Neural Networks [51.19164318924997]
  We show that existing detection mechanisms can be extremely brittle when evaluating on in-distribution and OOD inputs. We propose an effective algorithm called ALOE, which performs robust training by exposing the model to both adversarially crafted inlier and outlier examples.
  arXiv  Detail & Related papers  (2020-03-21T17:46:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.