Timezone: »

 
Out-of-Distribution Detection and Selective Generation for Conditional Language Models
Jie Ren · Jiaming Luo · Yao Zhao · Kundan Krishna · Mohammad Saleh · Balaji Lakshminarayanan · Peter Liu

Fri Dec 02 12:35 PM -- 12:45 PM (PST) @
in Robustness in Sequence Modeling »
Event URL: https://openreview.net/forum?id=toCkQQMxW8 »

Much work has shown that high-performing ML classifiers can degrade significantly and provide overly-confident, wrong classification predictions, particularly for out-of-distribution (OOD) inputs. Conditional language models (CLMs) are predominantly trained to classify the next token in an output sequence, and may suffer even worse degradation on out-of-distribution (OOD) inputs as the prediction is done auto-regressively over many steps. We present a highly accurate and lightweight OOD detection method for CLMs, and demonstrate its effectiveness on abstractive summarization and translation. We also show how our method can be used under the common and realistic setting of distribution shift for selective generation of high-quality outputs, while automatically abstaining from low-quality ones, enabling safer deployment of generative language models.

Author Information

Jie Ren (Google Brain)
Jiaming Luo (Google)
Yao Zhao (Google)
Kundan Krishna (Carnegie Mellon University)
Mohammad Saleh (Google)
Balaji Lakshminarayanan (Google Brain)

Balaji Lakshminarayanan is a research scientist at Google Brain. Prior to that, he was a research scientist at DeepMind. He received his PhD from the Gatsby Unit, University College London where he worked with Yee Whye Teh. His recent research has focused on probabilistic deep learning, specifically, uncertainty estimation, out-of-distribution robustness and deep generative models. Notable contributions relevant to the tutorial include developing state-of-the-art methods for calibration under dataset shift (such as deep ensembles and AugMix) and showing that deep generative models do not always know what they don't know. He has co-organized several workshops on "Uncertainty and Robustness in deep learning" and served as Area Chair for NeurIPS, ICML, ICLR and AISTATS.

Peter Liu (Google Research, Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors