mlsanityData to 7 Oct 2026

FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score

arXiv 2310.05083 ↗First posted 8 Oct 2023cs.LG cs.AI cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Detecting out-of-distribution (OOD) instances is crucial for NLP models in practical applications. Although numerous OOD detection methods exist, most of them are empirical. Backed by theoretical analysis, this paper advocates for the measurement of the "OOD-ness" of a test case boldsymbolx through the likelihood ratio between out-distribution mathcal P_textitout and in-distribution mathcal P_textitin. We argue that the state-of-the-art (SOTA) feature-based OOD detection methods, such as Maha and KNN, are suboptimal since they only estimate in-distribution density p_textitin(boldsymbolx). To address this issue, we propose FLatS, a principled solution for OOD detection based on likelihood ratio. Moreover, we demonstrate that FLatS can serve as a general framework capable of enhancing other OOD detection methods by incorporating out-distribution density p_textitout(boldsymbolx) estimation. Experiments show that FLatS establishes a new SOTA on popular benchmarks. Our code is publicly available at https://github.com/linhaowei1/FLatS.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 8 Oct 2023.

Builds on

26 of 40 references.

References · 26

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  4. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  6. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  7. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  8. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  9. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  10. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  11. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  12. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
14 more
  1. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  2. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  3. 2023Continual Pre-training of Language Modelscited by 194
  4. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  5. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  6. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  7. 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
  8. 2022Continual Training of Language Models for Few-Shot Learningcited by 33
  9. 2021Unsupervised Out-of-Domain Detection via Pre-trained Transformerscited by 31
  10. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  11. 2023Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Featurescited by 12
  12. 2023Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detectioncited by 9
  13. 2022Falsehoods that ML researchers believe about OOD detectioncited by 8
  14. 2020Natural Language Processing with Deep Learning for Medical Adverse Event Detection from Free-Text Medical Narratives: A Case Study of Detecting Total Hip Replacement Dislocationcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2025Shh, don't say that! Domain Certification in LLMscited by 7
  2. 2024Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regressioncited by 3
  3. 2025Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networkscited by 3
  4. 2024Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classificationcited by 2
  5. 2024One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learningcited by 0