2307.05300.pdf- “Unleashing the Emergent Cognitive Synergy in Large Language Models” – “Enhancing Problem-Solving with Multi-Persona Self-Collaboration in Language Models” – “Reducing Factual Hallucination and Improving Reasoning in Language Models” – “Comparative Analysis of Cognitive Synergy in GPT-4 and Less Capable Models” – “Exploring the Potential of Solo Performance Prompting in Language Models”

– Large language models (LLMs) face challenges in knowledge-intensive and reasoning-intensive tasks.
– Current LLMs lack cognitive synergy and slow-thinking capabilities.
– Previous works have enhanced reasoning abilities but struggle with factual hallucination.
– Solo Performance Prompting (SPP) unleashes cognitive synergy in LLMs through multi-persona self-collaboration.
– SPP improves problem-solving abilities and reduces factual hallucination.
– SPP is evaluated on Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle tasks.
– Cognitive synergy only emerges in GPT-4 and not in less capable models.

– GPT-4 is used in the task-solving example of Solo Performance Prompting (SPP).
– GPT-4 is capable of identifying personas based on task input.
– GPT-4 improves answer quality and provides accurate information compared to Standard Prompting.
– GPT-4 is part of the cognitive synergist agent created in this work.
– GPT-4 is compared to less capable models like GPT-3.5-turbo and Llama2-13b-chat.

– Solo Performance Prompting (SPP) enhances problem-solving abilities in complex tasks.
– SPP reduces factual hallucination and maintains strong reasoning capabilities.
– Cognitive synergy emerges in GPT-4 but not in less capable models.

– The paper proposes Solo Performance Prompting (SPP) to enhance problem-solving in large language models.
– SPP engages in multi-turn self-collaboration with multiple personas to unleash cognitive synergy.
– SPP improves problem-solving abilities and reduces factual hallucination in LLMs.
– SPP outperforms baselines significantly in challenging tasks.
– Cognitive synergy only emerges in GPT-4 and not in less capable models.

– Solo Performance Prompting (SPP) improves problem-solving abilities in large language models.
– SPP reduces factual errors and hallucinations in generated text.
– SPP outperforms other baselines significantly in challenging tasks.
– Cognitive synergy only emerges in GPT-4 and not in less capable models.

– Full results of the three tasks: Trivia Creative Writing, Codenames Collaborative, and Logic Grid Puzzle can be found in Tables 5, 6, and 7, respectively.

– Solo Performance Prompting (SPP) helps a computer program think like different people.
– It uses different personas to solve problems and get accurate knowledge.
– SPP reduces mistakes and makes better plans compared to other methods.
– It works well in tasks like writing stories and solving puzzles.
– SPP is better in GPT-4 model compared to other models.