Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning

• URL: http://arxiv.org/abs/2210.08830v1
• Date: Mon, 17 Oct 2022 08:19:01 GMT
• Title: Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
• Authors: Yanan Wu, Zhiyuan Zeng, Keqing He, Yutao Mou, Pei Wang, Yuanmeng Yan, Weiran Xu
• Abstract summary: We propose a simple but strong energy-based score function to detect OOD where the energy scores of OOD samples are higher than IND samples. Comprehensive experiments and analysis prove our method helps disentangle confidence score distributions of IND and OOD data.
• Score: 40.96874034407684
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. Traditional softmax-based confidence scores are susceptible to the overconfidence issue. In this paper, we propose a simple but strong energy-based score function to detect OOD where the energy scores of OOD samples are higher than IND samples. Further, given a small set of labeled OOD samples, we introduce an energy-based margin objective for supervised OOD detection to explicitly distinguish OOD samples from INDs. Comprehensive experiments and analysis prove our method helps disentangle confidence score distributions of IND and OOD data.\footnote{Our code is available at \url{https://github.com/pris-nlp/EMNLP2022-energy_for_OOD/}.}

Related papers

• The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection [75.65876949930258]
  Out-of-distribution (OOD) detection is essential for model trustworthiness. We show that the superior OOD detection performance of state-of-the-art methods is achieved by secretly sacrificing the OOD generalization ability.
  arXiv  Detail & Related papers  (2024-10-12T07:02:04Z)
• Taming False Positives in Out-of-Distribution Detection with Human Feedback [6.192472816262214]
  We propose a mathematically grounded OOD detection framework that leverages expert feedback to emphsafely update the threshold on the fly. We provide theoretical results showing that it is guaranteed to meet the FPR constraint at all times while minimizing the use of human feedback.
  arXiv  Detail & Related papers  (2024-04-25T18:06:47Z)
• APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection [40.846633965439956]
  This paper focuses on a few-shot OOD setting where there are only a few labeled IND data and massive unlabeled mixed data. We propose an adaptive pseudo-labeling (APP) method for few-shot OOD detection.
  arXiv  Detail & Related papers  (2023-10-20T09:48:52Z)
• Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective [55.45202687256175]
  Out-of-distribution (OOD) detection methods assume that they have test ground truths, i.e., whether individual test samples are in-distribution (IND) or OOD. In this paper, we are the first to introduce the unsupervised evaluation problem in OOD detection. We propose three methods to compute Gscore as an unsupervised indicator of OOD detection performance.
  arXiv  Detail & Related papers  (2023-02-16T13:34:35Z)
• Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data [41.62897997865578]
  Key ingredient to ensure safe system behaviour is Out-Of-Distribution detection. Most methods rely on hidden features output by the encoder. In this work, we focus on leveraging soft-probabilities in a black-box framework.
  arXiv  Detail & Related papers  (2022-12-18T21:22:28Z)
• Provably Robust Detection of Out-of-distribution Data (almost) for free [124.14121487542613]
  Deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data. In this paper we propose a novel method where from first principles we combine a certifiable OOD detector with a standard classifier into an OOD aware classifier. In this way we achieve the best of two worlds: certifiably adversarially robust OOD detection, even for OOD samples close to the in-distribution, without loss in prediction accuracy and close to state-of-the-art OOD detection performance for non-manipulated OOD data.
  arXiv  Detail & Related papers  (2021-06-08T11:40:49Z)
• Energy-based Out-of-distribution Detection [24.320646820385065]
  We propose a unified framework for OOD detection that uses an energy score. We show that energy scores better distinguish in- and out-of-distribution samples than the traditional approach. With energy-based training, our method outperforms the state-of-the-art on common benchmarks.
  arXiv  Detail & Related papers  (2020-10-08T04:42:17Z)
• ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining [51.19164318924997]
  Adrial Training with informative Outlier Mining improves robustness of OOD detection. ATOM achieves state-of-the-art performance under a broad family of classic and adversarial OOD evaluation tasks.
  arXiv  Detail & Related papers  (2020-06-26T20:58:05Z)
• 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.