paper-with-me

홈 › Papers

RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning

2026-05-13 · Andrea Morandi arxiv

LLM-as-a-judge is now the default measurement instrument for open-ended generation, but on the public JudgeBench benchmark even strong instruction-tuned judges barely scrape past random on objective-correctness pairwise items. We introduce RTLC, a three-stage prompting recipe -- Research, Teach-to-Learn, Critique -- that promotes a single black-box LLM into an ensemble-of-thought judge with no fine-tuning, retrieval, or external tools. Stage 1 wraps the input in a fixed pedagogical scaffold porting the Feynman Learning Technique (study $\to$ teach $\to$ find gaps $\to$ simplify) into LLM prompting. Stage 2 draws N=10 independent candidate verdicts at temperature 0.4. Stage 3 acts as its own critic, cross-comparing the candidate set against the original question to emit one critiqued verdict at temperature 0. On JudgeBench-GPT (350 hard pairwise items), Claude 3.7 Sonnet's pairwise accuracy climbs from 64.6% (single-shot vanilla prompt) to 78.6% (RTLC critique-of-10) -- an absolute 14.0-percentage-point gain. RTLC also beats N=10 self-consistency majority voting (77.7%) and a zero-shot first candidate (74.0%). A clean three-step ablation attributes +9.4 pp to the Teach-to-Learn scaffold, +3.7 pp to N=10 marginalisation, and +0.9 pp to explicit critique. We discuss the cost-accuracy frontier (RTLC sits above self-consistency at every working point), the error-budget breakdown across the four JudgeBench categories (knowledge, reasoning, math, coding), and how RTLC composes orthogonally with post-hoc judge-score calibration, with the two interventions compounding multiplicatively in practice.

📄 PDF Abstract BibTeX arXiv:2605.13695

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Robust Taylor-Lagrange Control for Safety-Critical Systems

2026-02-23 · Wei Xiao, Christos Cassandras, Anni Li arxiv

Solving safety-critical control problem has widely adopted the Control Barrier Function (CBF) method. However, the existence of a CBF is only a sufficient condition for system safety. The recently proposed Taylor-Lagrang…

Learning from Self Critique and Refinement for Faithful LLM Summarization

2025-12-05 · Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Cem Koc 외 arxiv

Large Language Models (LLMs) often suffer from hallucinations: output content that is not grounded in the input context, when performing long-form text generation tasks such as summarization. Prior works have shown that …

Self-Supervised LearningText Generation

Critique-Guided Distillation: Improving Supervised Fine-tuning via Better Distillation

2025-05-16 · Berkcan Kapusuzoglu, Supriyo Chakraborty, Chia-Hsuan Lee, Sambit Sahu

Supervised fine-tuning (SFT) using expert demonstrations often suffer from the imitation problem, where the model learns to reproduce the correct responses without \emph{understanding} the underlying rationale. To addres…

MathMMLUTriplet

CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving

2026-07-05 · Zhaohong Liu, Hao Ye, Xianlin Zhang, Mengshi Qi arxiv

End-to-end Vision-Language Models (VLMs) show immense potential in autonomous driving. However, standard Supervised Fine-Tuning (SFT) often suffers from reasoning hallucinations and conservative biases. While traditional…

Reinforcement LearningAutonomous Driving

RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation

2025-02-13 · Changzhi Zhou, Xinyu Zhang, Dandan song, Xiancai Chen 외

Code generation has attracted increasing attention with the rise of Large Language Models (LLMs). Many studies have developed powerful code LLMs by synthesizing code-related instruction data and applying supervised fine-…

Code Generation