Pith. sign in

What learning algorithm is in-context learning? I nvestigations with linear models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Lightweight Latent Verifiers for Efficient Meta-Generation Strategies

cs.AI · 2025-04-23 · conditional · novelty 5.0

LiLaVe, an XGBoost verifier trained on hidden states of a base LLM, predicts answer correctness with AUC comparable to large LLM-based verifiers, and enables conditional majority voting and self-correction that improve accuracy under fixed generation budgets.

citing papers explorer

Showing 1 of 1 citing paper.

  • Lightweight Latent Verifiers for Efficient Meta-Generation Strategies cs.AI · 2025-04-23 · conditional · none · ref 4

    LiLaVe, an XGBoost verifier trained on hidden states of a base LLM, predicts answer correctness with AUC comparable to large LLM-based verifiers, and enables conditional majority voting and self-correction that improve accuracy under fixed generation budgets.