arXiv Computation and Language
Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling Curves
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
4d ago
Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks
arXiv:2609.37493v1 Announce Type: cross Abstract: Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error...
arXiv AI
Aug 19
Grading Needs a Rubric, Not Intelligence
Small language models can grade open‑ended exam answers as reliably as much larger models when they use an explicit rubric. In experiments with six cost‑efficient model configurations, the rubric decouples grading from judge intelligence, with answer identity explaining 95.6% of score variance and judge identity only 0.2%. Removing rubric criteria or the official answer collapses reliability and inflates scores, showing the rubric’s essential role.
arXiv AI
Sep 25
Sharp Limits for Honest Uncertainty in Hard-Budget Repeated Evaluation
arXiv:2609. 29140v1 Announce Type: new Abstract: Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty.
arXiv Machine Learning
Aug 4
When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design
arXiv:2608. 01378v1 Announce Type: new Abstract: Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensive evaluation - an experiment, a first-principles simulation, or a full training run.
arXiv AI
Sep 24
Ask Which, Not How Good: Sizing Benchmarks Scored by an LLM
The study analyzes 373,019 judgments from LLM‑scored benchmarks, decomposing variance into system, item, judge, and interaction components via generalizability theory. It finds that with a single judge, generalizability converges to a ceiling determined by the system‑by‑judge variance, which is substantially lower in pairwise preference settings, allowing one judge to suffice. The research also reveals significant biases in presentation order and highlights that many published win‑rate claims fall below the measured floor of the benchmarks.
arXiv AI
Jun 15
The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation
arXiv:2606. 13685v1 Announce Type: cross Abstract: LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized.