Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Analyzing Nobel Prize Literature with Large Language Models

Zhenyuan Yang, Zhengliang Liu, Jing Zhang, Cen Lu, Jiaxin Tai, Tianyang Zhong, Yiwei Li, Siyan Zhao, Teng Yao, Qing Liu, Jinlin Yang, Qixin Liu, Zhaowei Li, Kexin Wang, Longjun Ma, Dajiang Zhu, Yudan Ren, Bao Ge, Wei Zhang, Ning Qiang, Tuo Zhang, Tianming Liu

TL;DR

This study probes how a state-of-the-art o1 large language model analyzes Nobel Prize literature by directly comparing its analyses with graduate-level human critiques on two short stories, Han Kang's Nine Chapters and Jon Fosse's Friendship. It employs a mixed-methods framework with qualitative appropriateness and quantitative scores (coherence, creativity, fidelity) to assess thematic depth, intertextuality, cultural-historical context, linguistic innovation, and character development. Findings indicate that the AI provides broad, text-faithful analyses and strong cross-cultural linkages, but lags humans in coherence and emotional nuance, though it sometimes surpasses humans in certain creative and fidelity dimensions. The results suggest valuable human-AI collaboration in the humanities, where AI handles structured, content-aligned analysis and humans supply interpretive, affective, and context-rich insight, paving the way for augmented literary scholarship and new pedagogical approaches.

Abstract

This study examines the capabilities of advanced Large Language Models (LLMs), particularly the o1 model, in the context of literary analysis. The outputs of these models are compared directly to those produced by graduate-level human participants. By focusing on two Nobel Prize-winning short stories, 'Nine Chapters' by Han Kang, the 2024 laureate, and 'Friendship' by Jon Fosse, the 2023 laureate, the research explores the extent to which AI can engage with complex literary elements such as thematic analysis, intertextuality, cultural and historical contexts, linguistic and structural innovations, and character development. Given the Nobel Prize's prestige and its emphasis on cultural, historical, and linguistic richness, applying LLMs to these works provides a deeper understanding of both human and AI approaches to interpretation. The study uses qualitative and quantitative evaluations of coherence, creativity, and fidelity to the text, revealing the strengths and limitations of AI in tasks typically reserved for human expertise. While LLMs demonstrate strong analytical capabilities, particularly in structured tasks, they often fall short in emotional nuance and coherence, areas where human interpretation excels. This research underscores the potential for human-AI collaboration in the humanities, opening new opportunities in literary studies and beyond.

Analyzing Nobel Prize Literature with Large Language Models

TL;DR

This study probes how a state-of-the-art o1 large language model analyzes Nobel Prize literature by directly comparing its analyses with graduate-level human critiques on two short stories, Han Kang's Nine Chapters and Jon Fosse's Friendship. It employs a mixed-methods framework with qualitative appropriateness and quantitative scores (coherence, creativity, fidelity) to assess thematic depth, intertextuality, cultural-historical context, linguistic innovation, and character development. Findings indicate that the AI provides broad, text-faithful analyses and strong cross-cultural linkages, but lags humans in coherence and emotional nuance, though it sometimes surpasses humans in certain creative and fidelity dimensions. The results suggest valuable human-AI collaboration in the humanities, where AI handles structured, content-aligned analysis and humans supply interpretive, affective, and context-rich insight, paving the way for augmented literary scholarship and new pedagogical approaches.

Abstract

This study examines the capabilities of advanced Large Language Models (LLMs), particularly the o1 model, in the context of literary analysis. The outputs of these models are compared directly to those produced by graduate-level human participants. By focusing on two Nobel Prize-winning short stories, 'Nine Chapters' by Han Kang, the 2024 laureate, and 'Friendship' by Jon Fosse, the 2023 laureate, the research explores the extent to which AI can engage with complex literary elements such as thematic analysis, intertextuality, cultural and historical contexts, linguistic and structural innovations, and character development. Given the Nobel Prize's prestige and its emphasis on cultural, historical, and linguistic richness, applying LLMs to these works provides a deeper understanding of both human and AI approaches to interpretation. The study uses qualitative and quantitative evaluations of coherence, creativity, and fidelity to the text, revealing the strengths and limitations of AI in tasks typically reserved for human expertise. While LLMs demonstrate strong analytical capabilities, particularly in structured tasks, they often fall short in emotional nuance and coherence, areas where human interpretation excels. This research underscores the potential for human-AI collaboration in the humanities, opening new opportunities in literary studies and beyond.

Paper Structure

This paper contains 42 sections, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Applications of LLMs in Text Analysis
  4. Cultural and Historical Contexts Analysis by LLMs
  5. Enhancing Reliability and Contextual Understanding in LLMs
  6. Moral and Psychological Dimensions of LLMs
  7. LLMs in Literary Evaluation
  8. Experiments and Observation
  9. Experimental Design
  10. Evaluation on Analysis of "Friendship"
  11. Qualitative Evaluation
  12. Coherence
  13. Creativity
  14. Fidelity to the Text
  15. Thematic Analysis
  16. ...and 27 more sections

Figures (2)

  • Figure 1: Character Development in Nobel Prize Literature "Friendship". This figure illustrates the development of central characters in the Nobel Prize-winning literary work, comparing human analysis and the o1 model's response.
  • Figure 2: Thematic Analysis in Nobel Prize Literature "Nine Chapters". This figure presents an analysis of the central themes in the Nobel Prize-winning literary work, comparing human analysis and the o1 model's response.