We present a novel approach to calibrating linguistic expressions of certainty, e.g., "Maybe" and "Likely". Unlike prior work that assigns a single score to each certainty phrase, we model uncertainty as distributions over the simplex to capture their semantics more accurately. To accommodate this new representation of certainty, we generalize existing measures of miscalibration and introduce a novel post-hoc calibration method. Leveraging these tools, we analyze the calibration of both humans (e.g., radiologists) and computational models (e.g., language models) and provide interpretable suggestions to improve their calibration. Measuring the calibration of humans and computational models is crucial. For example, in healthcare, radiologists express uncertainty in natural language (e.g., "Likely pneumonia") due to the inherent ambiguity in the image they examine. Additionally, it's more natural for large language models (LLMs) to express their confidence using certainty phrases since humans struggle with precise probability estimates (Zhang & Maloney, 2012). Our work enables measuring the calibration of both data annotators and LLMs, paving ways for future work to improve the reliability of LLMs. Existing miscalibration measures focus on classifiers that provide a confidence score, e.g., posterior probability. These approaches cannot be applied directly to text written by humans or language models that communicate uncertainty using natural language. Prior work on "verbalized confidence" attempted to address this by mapping certainty phrases to fixed probabilities, e.g., "High Confidence" equals "90% confident", (Lin et al., 2022a). The oversimplification misses two key aspects: (1) individual semantics: people use phrases like "High Confidence" to indicate a range (e.g., 80-100%) rather than a single value; and (2) population-level variation: different individuals may interpret the same certainty phrase differently. Appendix D explains this gap in more detail. Calibration in the space of certainty phrases presents unique challenges. Prior work such as histogram binning (Zadrozny & Elkan, 2001) and Platt scaling (Platt, 2000) fit low-dimensional functions (e.g., one-dimensional for binary classifiers) to map uncalibrated confidence scores to calibrated probabilities. However, when working with certainty phrases, direct manipulation of the underlying confidence scores is not feasible. In this work, we measure and calibrate both humans and computational models that convey their confidence using natural language expressions of certainty. The key idea is to treat certainty phrases as distributions over the probability simplex.

We aim to select data subsets for the fine-tuning of large language models to more effectively follow instructions. Prior work has emphasized the importance of diversity in dataset curation but relied on heuristics such as the number of tasks. In this paper, we use determinantal point processes to capture the diversity and quality of instruction tuning datasets for subset selection. We propose to measure dataset diversity with log determinant distance that is the distance between the dataset of interest and a maximally diverse reference dataset. Our experiments demonstrate that the proposed diversity measure in the normalized weight gradient space is correlated with downstream instruction-following performance. Consequently, it can be used to inform when data selection is the most helpful and to analyze dataset curation strategies. We demonstrate the utility of our approach on various instruction tuning datasets.

Self-supervised representation learning on image-text data facilitates crucial medical applications, such as image classification, visual grounding, and cross-modal retrieval. One common approach involves contrasting semantically similar (positive) and dissimilar (negative) pairs of data points. Drawing negative samples uniformly from the training data set introduces false negatives, i.e., samples that are treated as dissimilar but belong to the same class. In healthcare data, the underlying class distribution is nonuniform, implying that false negatives occur at a highly variable rate. To improve the quality of learned representations, we develop a novel approach that corrects for false negatives. Our method can be viewed as a variant of debiased contrastive learning that uses estimated sample-specific class probabilities. We provide theoretical analysis of the objective function and demonstrate the proposed approach on both image and paired image-text data sets. Our experiments illustrate empirical advantages of sample-specific debiasing.

Large Language Models (LLMs) have made remarkable advancements in the field of natural language processing. However, their increasing size poses challenges in terms of computational cost. On the other hand, Small Language Models (SLMs) are known for their efficiency, but they often struggle with limited capacity and training data, especially in specific domains. In this paper, we introduce a novel method aimed at improving SLMs in the medical domain using LLM-based generative data augmentation. The objective of our approach is to develop more efficient and capable models that are specifically tailored for specialized applications. Through experiments conducted on the PubMedQA dataset, we demonstrate the effectiveness of LLMs in refining and diversifying existing question-answer pairs. This refinement process leads to improved performance in a significantly smaller model after fine-tuning. Notably, our best SLM, with under 1.6 billion parameters, outperforms the few-shot GPT-4 on the PubMedQA dataset. Our code and generated data are publicly available to facilitate further explorations [1].

Quantization is a promising technique to reduce the model size, memory footprint, and massive computation operations of recurrent neural networks (RNNs) for embedded devices with limited resources. Although extreme low-bit quantization has achieved impressive success on convolutional neural networks, it still suffers from huge accuracy degradation on RNNs with the same low-bit precision. In this paper, we first investigate the accuracy degradation on RNN models under different quantization schemes, and the distribution of tensor values in the full precision model. Our observation reveals that due to the difference between the distributions of weights and activations, different quantization methods are suitable for different parts of models. Based on our observation, we propose HitNet, a hybrid ternary recurrent neural network, which bridges the accuracy gap between the full precision model and the quantized model. In HitNet, we develop a hybrid quantization method to quantize weights and activations. Moreover, we introduce a sloping factor motivated by prior work on Boltzmann machine to activation functions, further closing the accuracy gap between the full precision model and the quantized model. Overall, our HitNet can quantize RNN models into ternary values, {-1, 0, 1}, outperforming the state-of-the-art quantization methods on RNN models significantly. We test it on typical RNN models, such as Long-Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), on which the results outperform previous work significantly. For example, we improve the perplexity per word (PPW) of a ternary LSTM on Penn Tree Bank (PTB) corpus from 126 (the state-of-the-art result to the best of our knowledge) to 110.3 with a full precision model in 97.2, and a ternary GRU from 142 to 113.5 with a full precision model in 102.7.

Quantization is a promising technique to reduce the model size, memory footprint, and massive computation operations of recurrent neural networks (RNNs) for embedded devices with limited resources. Although extreme low-bit quantization has achieved impressive success on convolutional neural networks, it still suffers from huge accuracy degradation on RNNs with the same low-bit precision. In this paper, we first investigate the accuracy degradation on RNN models under different quantization schemes, and the distribution of tensor values in the full precision model. Our observation reveals that due to the difference between the distributions of weights and activations, different quantization methods are suitable for different parts of models. Based on our observation, we propose HitNet, a hybrid ternary recurrent neural network, which bridges the accuracy gap between the full precision model and the quantized model. In HitNet, we develop a hybrid quantization method to quantize weights and activations. Moreover, we introduce a sloping factor motivated by prior work on Boltzmann machine to activation functions, further closing the accuracy gap between the full precision model and the quantized model. Overall, our HitNet can quantize RNN models into ternary values, {-1, 0, 1}, outperforming the state-of-the-art quantization methods on RNN models significantly. We test it on typical RNN models, such as Long-Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), on which the results outperform previous work significantly. For example, we improve the perplexity per word (PPW) of a ternary LSTM on Penn Tree Bank (PTB) corpus from 126 (the state-of-the-art result to the best of our knowledge) to 110.3 with a full precision model in 97.2, and a ternary GRU from 142 to 113.5 with a full precision model in 102.7.