← Back to all news
arXiv Machine Learning By Soundouss Messoudi, Youness Mansar

Calibration and Risk-Budgeted Decisions with System One Models

Read the original on arXiv Machine Learning →

The paper investigates how large language model (LLM) workflows and agents make binary decisions—such as allowing or blocking an input—when human deferral is not possible. It proposes using System One decision scores that default to a conservative fallback in uncertain cases and control false omission risk within the subset of inputs that receive the utility‑maximizing action. Experiments on six datasets spanning moderation, safety, and reranking show that naive threshold baselines often exceed target risk, whereas a Learn‑Then‑Test approach achieves only 7.8% risk, demonstrating the limitations of probability‑like interfaces and the benefits of risk‑budgeted selection.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

Hugging Face Trending Papers
Aug 18

Judge, Retrieve, or Abstain: Uncertainty-Guarded LLM Judging with Provable Risk Guarantees

The paper introduces a risk‑controlled framework for using large language models (LLMs) as judges in tasks without reference answers. By calibrating uncertainty thresholds on a held‑out set, the method ensures that the false discovery rate of accepted verdicts stays below a user‑specified level α with high probability, using finite‑sample Clopper–Pearson intervals. When the parametric judge lacks confidence, the instance is routed to a retrieval‑augmented mode with a second calibrated threshold, preserving the error guarantee while achieving higher coverage than single‑mode baselines.

llmsragbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 29

Auditing System-1 Models on Biosecurity-Relevant Benchmarks: Calibration, Selective Prediction, and Permutation Instability in a Non-Generative Model

The paper audits a commercial non‑generative System‑1 model on biosecurity‑relevant benchmarks, evaluating accuracy, calibration, error detection, selective prediction, and sensitivity to answer‑option order. It finds that the model’s accuracy varies strongly by task, is reasonably well calibrated when the vendor’s uncertainty field is interpreted correctly, and that option order can cause significant prediction changes—averaging across rotations improves accuracy. The study also shows that applying averaging only to low‑confidence items recovers most of the gain at a lower cost.

By Kimon Antonios Provatas, Ilias Georgakopoulos-Soares
benchmarks
More like this →