LLMs trace moral history across 9,000 novel plot summaries in new computational literary studies framework
_akpiper · x · 2026-11-20
Andrew Piper's 2025 paper in the Journal of Computational Literary Studies introduces a framework using LLMs to trace the implicit and explicit life lessons conveyed by fiction over time.
- Moral history: studying the life lessons, values, and ethical takeaways encoded in stories across periods and cultures
- Perspectival approach: treating moral extraction as interpretation from a specific vantage point, not a fixed taxonomy
- Corpus: over 9,000 Wikipedia plot summaries of 20th- and 21st-century novels
- Workflow: narrative summarization and moralization, then mapping broader structures via co-occurrence networks and hierarchical clustering
- Handling variability: randomized prompt assignments account for differences in how LLMs phrase story morals, enabling cross-model and cross-period comparison
Related work is available via Piper's publications and McGill's .txtlab.
More from Research
- Mathematician claims Riemann Hypothesis proof with Claude: 17.3M lines of Lean, unverified — imjustnewatai · 2026-11-21
- Riemann Hypothesis proof claim released as Lean formalization on Papers with Code — Michael_D_Moor · 2026-11-21
- "Wright Brothers first flight for math": KOLs hail a new era after math breakthrough — jamesdouma · 2026-11-21
- Stanford-led paper: 27B open model rewrites its own weights, gains 6.6 points without training — rohanpaul_ai · 2026-11-21
- Language Models Can Rewrite Their Own Weights: 27B Model Self-Improves Without Gradients — Jiajun Fan · 2026-11-21
- Anthropic mathematician claims he and Claude proved the Riemann Hypothesis, formalized in Lean — NinaDSchick · 2026-11-21