Topic
verifier
Artificial Intelligence #formal theorem proving#ai
VERITAS Framework Uses Verifier Feedback to Boost Zero-Shot Theorem Proving Accuracy
VERITAS, a zero-shot framework for formal theorem proving, leverages all verifier signals rather than collapsing them into a binary pass/fail. It reaches 40.6% on the miniF2F benchmark, outperforming Best-of-5 (36.9%) and Portfolio (26.2%). On a new combinatorics benchmark, VERITAS scores 7.3% while unguided sampling falls to 1.8%, demonstrating the value of feedback-driven exploration.
Jun 20, 2026 1 source
Artificial Intelligence #llm#reasoning
Semi-Supervised Framework Scales LLM Reasoning Using 10-15x Fewer Labels Than Traditional Methods
A new semi-supervised framework for training LLM reasoning uses a lightweight verifier to judge reasoning quality, requiring only a few labeled samples. Experiments on math problems and visual question answering show accuracy comparable to 10-15x more labeled data. The method could reduce the cost of building large-scale reasoning datasets.
Jun 16, 2026 2 sources