Always Tell Me The Odds: Fine-grained Conditional Probability Estimation
This addresses the issue of unreliable uncertainty estimation in LLMs, which is crucial for applications requiring precise probability assessments, though it appears incremental as it builds on existing methods with improved supervision and scaling.
The paper tackles the problem of large language models struggling with accurate and calibrated probabilistic predictions under uncertainty, and presents a model that outperforms existing methods by a large margin in fine-grained conditional probability estimation tasks.
We present a state-of-the-art model for fine-grained probability estimation of propositions conditioned on context. Recent advances in large language models (LLMs) have significantly enhanced their reasoning capabilities, particularly on well-defined tasks with complete information. However, LLMs continue to struggle with making accurate and well-calibrated probabilistic predictions under uncertainty or partial information. While incorporating uncertainty into model predictions often boosts performance, obtaining reliable estimates of that uncertainty remains understudied. In particular, LLM probability estimates tend to be coarse and biased towards more frequent numbers. Through a combination of human and synthetic data creation and assessment, scaling to larger models, and better supervision, we propose a set of strong and precise probability estimation models. We conduct systematic evaluations across tasks that rely on conditional probability estimation and show that our approach consistently outperforms existing fine-tuned and prompting-based methods by a large margin.