Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector

• URL: http://arxiv.org/abs/2404.08679v1
• Date: Sun, 7 Apr 2024 10:32:49 GMT
• Title: Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
• Authors: Andi Zhang, Tim Z. Xiao, Weiyang Liu, Robert Bamler, Damon Wischik,
• Abstract summary: We revisit the likelihood ratio between a pretrained large language model (LLM) and its finetuned variant as a criterion for out-of-distribution (OOD) detection. We show that, for the first time, the likelihood ratio can serve as an effective OOD detector.
• Score: 17.305076703258813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We revisit the likelihood ratio between a pretrained large language model (LLM) and its finetuned variant as a criterion for out-of-distribution (OOD) detection. The intuition behind such a criterion is that, the pretrained LLM has the prior knowledge about OOD data due to its large amount of training data, and once finetuned with the in-distribution data, the LLM has sufficient knowledge to distinguish their difference. Leveraging the power of LLMs, we show that, for the first time, the likelihood ratio can serve as an effective OOD detector. Moreover, we apply the proposed LLM-based likelihood ratio to detect OOD questions in question-answering (QA) systems, which can be used to improve the performance of specialized LLMs for general questions. Given that likelihood can be easily obtained by the loss functions within contemporary neural network frameworks, it is straightforward to implement this approach in practice. Since both the pretrained LLMs and its various finetuned models are available, our proposed criterion can be effortlessly incorporated for OOD detection without the need for further training. We conduct comprehensive evaluation across on multiple settings, including far OOD, near OOD, spam detection, and QA scenarios, to demonstrate the effectiveness of the method.

Related papers

• A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs [74.35290684163718]
  A primary challenge in large language model (LLM) development is their onerous pre-training cost. This paper explores a promising paradigm to improve LLM pre-training efficiency and quality by leveraging a small language model (SLM)
  arXiv  Detail & Related papers  (2024-10-24T14:31:52Z)
• Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection [71.93411099797308]
  Out-of-distribution (OOD) samples are crucial when deploying machine learning models in open-world scenarios. We propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to potential Outlier Exposure, termed EOE. EOE can be generalized to different tasks, including far, near, and fine-language OOD detection. EOE achieves state-of-the-art performance across different OOD tasks and can be effectively scaled to the ImageNet-1K dataset.
  arXiv  Detail & Related papers  (2024-06-02T17:09:48Z)
• WeiPer: OOD Detection using Weight Perturbations of Class Projections [11.130659240045544]
  We introduce perturbations of the class projections in the final fully connected layer which creates a richer representation of the input. We achieve state-of-the-art OOD detection results across multiple benchmarks of the OpenOOD framework.
  arXiv  Detail & Related papers  (2024-05-27T13:38:28Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection [67.68030805755679]
  Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
  arXiv  Detail & Related papers  (2023-10-12T04:14:28Z)
• 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)
• How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models? [29.75562085178755]
  We study how fine-tuning impact OOD detection for few-shot downstream tasks. Our results suggest that a proper choice of OOD scores is essential for CLIP-based fine-tuning. We also show that prompt learning demonstrates the state-of-the-art OOD detection performance over the zero-shot counterpart.
  arXiv  Detail & Related papers  (2023-06-09T17:16:50Z)
• 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)
• Pseudo-OOD training for robust language models [78.15712542481859]
  OOD detection is a key component of a reliable machine-learning model for any industry-scale application. We propose POORE - POsthoc pseudo-Ood REgularization, that generates pseudo-OOD samples using in-distribution (IND) data. We extensively evaluate our framework on three real-world dialogue systems, achieving new state-of-the-art in OOD detection.
  arXiv  Detail & Related papers  (2022-10-17T14:32:02Z)
• Holistic Sentence Embeddings for Better Out-of-Distribution Detection [12.640837452980332]
  We propose a simple embedding approach named Avg-Avg, which averages all token representations from each intermediate layer as the sentence embedding. Our analysis demonstrates that it indeed helps preserve general linguistic knowledge in fine-tuned PLMs and substantially benefits detecting background shifts.
  arXiv  Detail & Related papers  (2022-10-14T03:22:58Z)

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.