Unstructured Minds, Predictable Machines: A Comparative Study of Narrative Cohesion in Human and LLM Stream-of-Consciousness Writing

This paper examines differences between stream-of-consciousness (SoC) narratives written by humans and those generated by large language models (LLMs) to assess narrative coherence and personality expression.We generated texts by prompting LLMs (Llama-3.1-8B& DeepSeek-R1-Distill-Llama-8B) with the first half of SoC-essays while either providing the models with the personality characteristics (Big Five) or omitting them.Our analysis revealed consistently low similarity between LLM-generated continuations and original human texts, as measured by cosine similarity, perplexity, and BLEU scores.Including explicit personality traits significantly enhanced Llama-3.1-8B'sperformance, particularly in BLEU scores.Further analysis of personality expression showed varying alignment patterns between LLMs and human texts.Specifically, Llama-3.1-8Bexhibited higher extraversion but low agreeableness, while DeepSeek-R1-Distill-Llama-8B displayed dramatic personality shifts during its reasoning process, especially when prompted with personality traits, with all models consistently showing very low Openness.