Prepending stochastic sequences from Lorem Ipsum vocabulary to prompts during GRPO resampling broadens reasoning exploration and outperforms standard resampling on hard tasks for 1.7B-7B models.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
MixRea benchmark reveals LLMs achieve at most 42.8% consistency on explicit-implicit reasoning tasks, with PRCP prompting proposed to recover overlooked relations.
Med-Gemini sets new records on 10 of 14 medical benchmarks including 91.1% on MedQA-USMLE, beats GPT-4V by 44.5% on multimodal tasks, and surpasses humans on medical text summarization.
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
Human-AI hybrids achieve only +0.4pp over AI alone on diverse tasks because confidence routing fails to identify the small set of cases where humans can correct AI errors.
A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.
citing papers explorer
-
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
Prepending stochastic sequences from Lorem Ipsum vocabulary to prompts during GRPO resampling broadens reasoning exploration and outperforms standard resampling on hard tasks for 1.7B-7B models.
-
RouterBench: A Benchmark for Multi-LLM Routing System
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
-
MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models
MixRea benchmark reveals LLMs achieve at most 42.8% consistency on explicit-implicit reasoning tasks, with PRCP prompting proposed to recover overlooked relations.
-
Capabilities of Gemini Models in Medicine
Med-Gemini sets new records on 10 of 14 medical benchmarks including 91.1% on MedQA-USMLE, beats GPT-4V by 44.5% on multimodal tasks, and surpasses humans on medical text summarization.
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
-
Toward Human-AI Complementarity Across Diverse Tasks
Human-AI hybrids achieve only +0.4pp over AI alone on diverse tasks because confidence routing fails to identify the small set of cases where humans can correct AI errors.
-
A Survey on Knowledge Distillation of Large Language Models
A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.