6 papers
Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
Liran Ringel, Ameen Ali, Yaniv Romano
Discrete diffusion language models (dLLMs) accelerate text generation by unmasking multiple tokens in parallel. However, parallel decoding introduces a distributional mismatch: it…
Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective
Osvaldo Simeone, Yaniv Romano
In context-specific applications such as robotics, telecommunications, and healthcare, artificial intelligence systems often face the challenge of limited training data. This scarc…
Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting
Shai Feldman, Stephen Bates, Yaniv Romano
We introduce a framework for robust uncertainty quantification in situations where labeled training data are corrupted, through noisy or missing labels. We build on conformal predi…
Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs
Hen Davidov, Shai Feldman, Gilad Freidkin +1
We introduce time-to-unsafe-sampling, a novel safety measure for generative models, defined as the number of generations required by a large language model (LLM) to trigger an unsa…
Robust Conformal Prediction Using Privileged Information
Shai Feldman, Yaniv Romano
We develop a method to generate prediction sets with a guaranteed coverage rate that is robust to corruptions in the training data, such as missing or noisy variables. Our approach…
Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach
Yarin Bar, Shalev Shaer, Yaniv Romano
We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution s…