Uncertainty Quantification (UQ) for Natural Language Generation (NLG) is crucial for assessing the performance of Large Language Models (LLMs), as it reveals confidence in predictions, identifies failure modes, and gauges output reliability. Conformal Prediction (CP), a model-agnostic method that generates prediction sets with a specified error rate, has been adopted for UQ in classification tasks, where the size of the prediction set indicates the model's uncertainty. However, when adapting CP to NLG, the sampling-based method for generating candidate outputs cannot guarantee the inclusion of the ground truth, limiting its applicability across a wide range of error rates. To address this, we propose \ourmethod, a method that explicitly adds the ground truth to the candidate outputs and uses logit scores to measure nonconformity. Our experiments with six LLMs on four NLG tasks show that \ourmethod outperforms baseline methods in calibrating error rates and empirical cover rates, offering accurate UQ across a wide range of user-specified error rates.

The learning objective is integral to collaborative filtering systems, where the Bayesian Personalized Ranking (BPR) loss is widely used for learning informative backbones. However, BPR often experiences slow convergence and suboptimal local optima, partially because it only considers one negative item for each positive item, neglecting the potential impacts of other unobserved items. To address this issue, the recently proposed Sampled Softmax Cross-Entropy (SSM) compares one positive sample with multiple negative samples, leading to better performance. Our comprehensive experiments confirm that recommender systems consistently benefit from multiple negative samples during training. Furthermore, we introduce a \underline{Sim}plified Sampled Softmax \underline{C}ross-\underline{E}ntropy Loss (SimCE), which simplifies the SSM using its upper bound. Our validation on 12 benchmark datasets, using both MF and LightGCN backbones, shows that SimCE significantly outperforms both BPR and SSM.

While the numerous parameters in Large Language Models (LLMs) contribute to their superior performance, this massive scale makes them inefficient and memory-hungry. Thus, they are hard to deploy on commodity hardware, such as one single GPU. Given the memory and power constraints of such devices, model compression methods are widely employed to reduce both the model size and inference latency, which essentially trades off model quality in return for improved efficiency. Thus, optimizing this accuracy-efficiency trade-off is crucial for the LLM deployment on commodity hardware. In this paper, we introduce a new perspective to optimize this trade-off by prompting compressed models. Specifically, we first observe that for certain questions, the generation quality of a compressed LLM can be significantly improved by adding carefully designed hard prompts, though this isn't the case for all questions. Based on this observation, we propose a soft prompt learning method where we expose the compressed model to the prompt learning process, aiming to enhance the performance of prompts. Our experimental analysis suggests our soft prompt strategy greatly improves the performance of the 8x compressed LLaMA-7B model (with a joint 4-bit quantization and 50% weight pruning compression), allowing them to match their uncompressed counterparts on popular benchmarks. Also, we demonstrate that these learned prompts can be transferred across various datasets, tasks, and compression levels. Hence with this transferability, we can stitch the soft prompt to a newly compressed model to improve the test-time accuracy in an ``in-situ'' way.

We carefully evaluate a number of algorithms for learning in a federated environment, and test their utility for a variety of image classification tasks. We consider many issues that have not been adequately considered before: whether learning over data sets that do not have diverse sets of images affects the results; whether to use a pre-trained feature extraction "backbone"; how to evaluate learner performance (we argue that classification accuracy is not enough), among others. Overall, across a wide variety of settings, we find that vertically decomposing a neural network seems to give the best results, and outperforms more standard reconciliation-used methods.

We consider the problem of how to differentiate In addition to scalability, executing such a code on a relational computations expressed relationally. We show engine has the advantage that the database query experimentally that a relational engine running an optimizer will automatically distribute the computation, taking auto-differentiated relational algorithm can easily into account the sizes of the two matrices. If A and B are scale to very large datasets, and is competitive both large matrices, a database optimizer will consider the with state-of-the-art, special-purpose systems for hardware constraints on each compute node (e.g.

Recently, Large Language Models (LLMs) have demonstrated remarkable capabilities. Chain-of-Thought (CoT) has been proposed as a way of assisting LLMs in performing complex reasoning. However, developing effective prompts can be a challenging and labor-intensive task. Many studies come out of some way to automatically construct CoT from test data. Most of them assume that all test data is visible before testing and only select a small subset to generate rationales, which is an unrealistic assumption. In this paper, we present a case study on how to construct and optimize chain-of-thought prompting using batch data in streaming settings.