Related papers: Believe Your Model: Distribution-Guided Confidence…

Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so by sharpening the distribution over full generated outputs, favoring completions that are…

Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across demographic groups due to differences in underlying beliefs. As Large Language Models (LLMs) are increasingly used to simulate human…

We are interested in probabilistic prediction in online settings in which data does not follow a probability distribution. Our work seeks to achieve two goals: (1) producing valid probabilities that accurately reflect model confidence; and…

We propose a methodology for constructing confidence regions with partially identified models of general form. The region is obtained by inverting a test of internal consistency of the econometric structure. We develop a dilation bootstrap…

Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-constrained settings. Existing approaches often depend on…

Conversational Question Answering (ConvQA) models aim at answering a question with its relevant paragraph and previous question-answer pairs that occurred during conversation multiple times. To apply such models to a real-world scenario,…

We consider the problem of distributed multi-choice voting in a setting that each node can communicate with its neighbors merely by sending beep signals. Given its simplicity, the beep communication model is of practical importance in…

Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning. Previous work has focused mainly on bounding either the expected loss of a predictor or the probability that an…

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

Distributed learning, particularly variants of distributed stochastic gradient descent (DSGD), are widely employed to speed up training by leveraging computational resources of several workers. However, in practise, communication delay…

Reasoning with large language models often benefits from generating multiple chains-of-thought, but existing aggregation strategies are typically trajectory-level (e.g., selecting the best trace or voting on the final answer), discarding…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Recommender systems based on graph neural networks perform well in tasks such as rating and ranking. However, in real-world recommendation scenarios, noise such as user misuse and malicious advertisement gradually accumulates through the…

Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample…

Adapting pretrained diffusion models to downstream objectives such as inverse problems often requires expensive test-time guidance or optimization. We propose a principled framework for generating high-quality reward-aligned samples at…

Question answering is one of the most important and difficult applications at the border of information retrieval and natural language processing, especially when we talk about complex science questions which require some form of inference…

Large Language Models (LLMs) have demonstrated remarkable self-improvement capabilities, whereby models iteratively revise their outputs through self-generated feedback. While this reflective mechanism has shown promise in enhancing task…

Instead of testing for unanimous agreement, I propose learning how broad of a consensus favors one distribution over another (of earnings, productivity, asset returns, test scores, etc.). Specifically, given a sample from each of two…

In regression problems where there is no known true underlying model, conformal prediction methods enable prediction intervals to be constructed without any assumptions on the distribution of the underlying data, except that the training…

Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…