Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate this issue, we propose a regularized fine-tuning method.Our method introduces two types of regularization for better calibration: (1) On-manifold regularization, which generates pseudo on-manifold samples through interpolation within the data manifold. Augmented training with these pseudo samples imposes a smoothness regularization to improve in-distribution calibration. (2) Off-manifold regularization, which encourages the model to output uniform distributions for pseudo off-manifold samples to address the over-confidence issue for OOD data. Our experiments demonstrate that the proposed method outperforms existing calibration methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets. Our code can be found at https://github.com/Lingkai-Kong/ Calibrated-BERT-Fine-Tuning.

Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate this issue, we propose a regularized fine-tuning method. Our method introduces two types of regularization for better calibration: (1) On-manifold regularization, which generates pseudo on-manifold samples through interpolation within the data manifold. Augmented training with these pseudo samples imposes a smoothness regularization to improve in-distribution calibration. (2) Off-manifold regularization, which encourages the model to output uniform distributions for pseudo off-manifold samples to address the over-confidence issue for OOD data. Our experiments demonstrate that the proposed method outperforms existing calibration methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets. Our code can be found at https://github.com/Lingkai-Kong/ Calibrated-BERT-Fine-Tuning.

With the progressive scale-down of semiconductor's feature size, people are looking forward to More Moore and More than Moore. In order to offer a possible alternative implementation process, people are trying to figure out a feasible transfer from silicon to molecular computing. Such transfer lies on bio-based modules programming with computer-like logic, aiming at realizing the Turing machine. To accomplish this, the DNA-based combinational logic is inevitably the first step we have taken care of. This timely overview paper introduces combinational logic synthesized in DNA computing from both analog and digital perspectives separately. State-of-the-art research progress is summarized for interested readers to quick understand DNA computing, initiate discussion on existing techniques and inspire innovation solutions. We hope this paper can pave the way for the future DNA computing synthesis.

No abstract

With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language generation (NLG) models, we propose a retrievalenhanced framework to create training data from a general-domain unlabeled corpus. To realize this, we first conduct contrastive pretraining to learn an unsupervised dense retriever for extracting most relevant documents using classdescriptive verbalizers. We then further propose two simple strategies, namely Verbalizer Augmentation with Demonstrations and Selfconsistency Guided Filtering to improve the topic coverage of the dataset while removing noisy examples. Experiments on nine datasets demonstrate that REGEN achieves 4.3% gain over strongest baselines and saves around 70% of the time when compared with baselines using large NLG models. Besides, REGEN can be naturally integrated with recently proposed large language models to boost performance 1 .