A survey of safety and trustworthiness of large language models through the lens of verification and validation

X Huang, W Ruan, W Huang, G Jin, Y Dong… - Artificial Intelligence …, 2024 - Springer
Large language models (LLMs) have exploded a new heatwave of AI for their ability to
engage end-users in human-level conversations with detailed and articulate answers across …

Distinguish sense from nonsense: Out-of-scope detection for virtual assistants

C Qian, H Qi, G Wang, L Kunc, S Potdar - arXiv preprint arXiv:2301.06544, 2023 - arxiv.org
Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a
conversation gracefully when it is unable to make sense of the end-user query. Accurately …

Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments

H Lee, H Byun, C Oh, JY Bak, K Song - ECAI 2024, 2024 - ebooks.iospress.nl
Accessing machine learning models through remote APIs has been gaining prevalence
following the recent trend of scaling up model parameters for increased performance. Even …

A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution

N Varshney, H Gupta, E Robertson, B Liu… - arXiv preprint arXiv …, 2023 - arxiv.org
State-of-the-art natural language processing models have been shown to achieve
remarkable performance in'closed-world'settings where all the labels in the evaluation set …

Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression

A Gulati, X Dong, C Hurtado, S Shekkizhar… - arXiv preprint arXiv …, 2024 - arxiv.org
As language models become more general purpose, increased attention needs to be paid to
detecting out-of-distribution (OOD) instances, ie, those not belonging to any of the …

Out-of-Scope Intent Detection with Supervised Deep Metric Learning

Y Zhang, X Wang, L Wang, K Yan… - 2023 International Joint …, 2023 - ieeexplore.ieee.org
Detecting Out-of-Scope (OOS) intents in dialogue systems is a challenging technique with
practical applications. As for OOS intent detection, it not only ensures the accuracy of …

Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al.(2021)

Y Zheng, G Chen - arXiv preprint arXiv:2205.11887, 2022 - arxiv.org
We have noticed that Marek et al.(2021) try to re-implement our paper Zheng et al.(2020a) in
their work" OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation" …