arXiv Statistics ML

A Unifying Perspective on Probabilities as Model Predictions

arXiv AI
Sep 10

When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs

The paper introduces a decision‑theoretic framework that elicits both probability judgments and decisions from large language models (LLMs) to test whether their reported beliefs are consistent with their actions. It shows that this framework yields empirically testable conditions without assuming a specific utility function. In clinical diagnosis simulations, the authors find that while LLMs’ reported beliefs are not perfect reflections of the information in their decisions, the discrepancies are small for the strongest models.

By Khurram Yamin, Jingjing Tang, Santiago Cortes-Gomez, Amit Sharma, Eric Horvitz, Bryan Wilder
arXiv Machine Learning
Jun 19

Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence

arXiv:2606. 19353v1 Announce Type: cross Abstract: In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its reliability remains a concern: predictions are highly sensitive to both prompt design and the model's ability to understand the context, obscuring whether failures arise from data properties or model limitations.

By Jinseok Chung, Minkyoung Song, Hyunji Jung, Namhoon Lee
arXiv Machine Learning
2d ago

Observational Multiplicity

The paper introduces the concept of observational multiplicity, where multiple probabilistic classifiers can perform similarly yet produce conflicting predictions, undermining interpretability and safety. It proposes measuring this arbitrariness through a regret metric that captures how predictions could shift with different training labels. The authors present a general method to estimate regret, show it varies across dataset groups, and discuss its use for safety via abstention and targeted data collection.

By Erin George, Deanna Needell, Berk Ustun
arXiv Machine Learning
Jul 9

Optimal Conformal Prediction under Epistemic Uncertainty

arXiv:2505. 19033v2 Announce Type: replace-cross Abstract: Conformal prediction (CP) is a widely used frequentist framework to quantify uncertainty by constructing prediction sets with user-specified marginal coverage guarantees.

By Alireza Javanmardi, Soroush H. Zargarbashi, Santo M. A. R. Thies, Willem Waegeman, Aleksandar Bojchevski, Eyke H\"ullermeier
arXiv AI
1d ago

Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization

The paper investigates how Large Language Models can be used to approximate domain expert priors for Bayesian Networks by extracting probabilistic knowledge about real‑world events. Experiments on eighty publicly available networks across domains such as healthcare and finance show that LLM‑derived conditional probabilities outperform random, uniform, and next‑token baselines. The authors also demonstrate that these LLM‑generated priors can refine data‑driven distributions, especially when data is scarce, and provide the first comprehensive baseline for evaluating LLM performance in probabilistic knowledge extraction.

By Aliakbar Nafar, Kristen Brent Venable, Zijun Cui, Parisa Kordjamshidi