VerifySteer selectively steers hidden states at paragraph boundaries using latent correctness signals to control verifier strictness and outperform baselines on ProcessBench and Hard2Verify with lower compute.
Scaling generative verifiers for natural language mathematical proof verification and selection.arXiv preprint arXiv:2511.13027
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Pseudo-Formalization decomposes proofs into self-contained natural language modules for independent LLM-based Block Verification, outperforming LLM-as-judge baselines on olympiad and research math benchmarks while releasing ArxivMathGradingBench.
CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced evaluation cost.
citing papers explorer
-
The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering
VerifySteer selectively steers hidden states at paragraph boundaries using latent correctness signals to control verifier strictness and outperform baselines on ProcessBench and Hard2Verify with lower compute.
-
Pseudo-Formalization for Automatic Proof Verification
Pseudo-Formalization decomposes proofs into self-contained natural language modules for independent LLM-based Block Verification, outperforming LLM-as-judge baselines on olympiad and research math benchmarks while releasing ArxivMathGradingBench.
-
CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval
CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced evaluation cost.