arXiv AI
Consider, Then Choose: Order-Invariant Decisions in System One Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 15
Prism-1: Position- and Rival-Independent Scoring for System One Models
Given a state and a set of options, such as intents, tools or interface elements, System One decision models return a distribution over the options in one forward pass, without generated reasoning. We...
arXiv AI
Oct 16
Prism-1: Position- and Rival-Independent Scoring for System One Models
Prism-1 introduces Position- and Rival-Independent Scoring for System One models, ensuring that option ordering and set changes do not affect decision probabilities. It achieves this by reading each option in its own block at shared positions, preserving softmax independence across options. Experiments on Qwen3-8B and Gemma 4 12B show Prism-1 maintains baseline accuracy while eliminating sensitivity to shuffling and irrelevant options.
arXiv Machine Learning
1d ago
Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters
The paper investigates how compact an encoder can be for closed‑set decision tasks in language‑model pipelines, comparing joint versus per‑option scoring. In a 32‑million‑parameter study, per‑option scoring outperforms joint scoring by 5.8 chance‑corrected skill points on a 37‑benchmark suite, and two external benchmarks corroborate this advantage. Across six released joint encoders ranging from 17 million to 1 billion parameters, the 68‑ and 150‑million‑parameter models surpass a 435‑million‑parameter DeBERTa‑v3 zero‑shot classifier on 209 overlapping tasks and match it on 145 unseen tasks, while the smallest model processes a median request in 14 ms versus 728 ms for the classifier.
arXiv Computation and Language
Oct 7
Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation
Prefill‑only decision models evaluate every candidate in a menu in a single forward pass, avoiding decoding and reducing cost by one to two orders of magnitude compared to generative language models. The paper demonstrates that when only the candidate menu changes, the model’s post‑intervention accuracy can be predicted solely from the cached first‑pass distribution using a simple estimator that renormalizes and selects the argmax, without any labels or second pass. Across seven model families, ten datasets, and two task types, this menu‑only intervention prediction is within 4.2 points of actual accuracy, and in one family it is exact, whereas a probability‑level variant fails by 21 points, indicating the property resides in ranking rather than calibrated probabilities.
arXiv AI
Oct 16
LEV: Thinking Fast and Deep with Looped Decision Models
LEV is a decision model that performs reasoning by looping its layers instead of generating text, allowing it to deepen its computation on a per-question basis. Trained jointly across all loop steps, a single LEV checkpoint can answer at any depth, improving accuracy—especially on hard questions—while keeping inference fast. On benchmark tests, LEV outperforms dense and cascade models by 5.4 to 8.8 accuracy points with sub‑50 ms latency, and on‑demand depth selection saves 15–24% of computation for minimal accuracy loss.
arXiv AI
Oct 7
SanSi: A Looped Typed Decision Model for System 1.5 Thinking
arXiv:2610.07730v1 Announce Type: cross Abstract: Typed decision models answer a declared question without generating text: a decision head returns a probability for each of the declared options in a...