# Large language models can segment narrative events similarly to humans

arXiv: https://arxiv.org/abs/2301.10297 · HTML: https://mlsanity.com/paper/2301.10297/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 48 references that are in the map.
- First posted on arXiv 24 Jan 2023.

## Builds on (most cited first, 5 of 5)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)](https://mlsanity.com/paper/1905.11833/) (2019)
- [Linguistic generalization and compositionality in modern artificial neural networks](https://mlsanity.com/paper/1904.00157/) (2019)
- [Towards mental time travel: a hierarchical memory for reinforcement learning agents](https://mlsanity.com/paper/2105.14039/) (2021)
- [Testing the limits of natural language models for predicting human language judgments](https://mlsanity.com/paper/2204.03592/) (2022)

## Built on by (most cited first, 16 of 16)

- [Evaluating Cognitive Maps and Planning in Large Language Models with CogEval](https://mlsanity.com/paper/2309.15129/) (2023)
- [Human-inspired Episodic Memory for Infinite Context LLMs](https://mlsanity.com/paper/2407.09450/) (2024)
- [Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents](https://mlsanity.com/paper/2502.06975/) (2025)
- [Augmenting Autotelic Agents with Large Language Models](https://mlsanity.com/paper/2305.12487/) (2023)
- [HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs](https://mlsanity.com/paper/2405.17633/) (2024)
- [Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey](https://mlsanity.com/paper/2602.15851/) (2026)
- [Large-scale study of human memory for meaningful narratives](https://mlsanity.com/paper/2311.04742/) (2023)
- [SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning](https://mlsanity.com/paper/2511.22367/) (2025)
- [Beyond checkmate: exploring the creative chokepoints in AI text](https://mlsanity.com/paper/2501.19301/) (2025)
- [Narrative-to-Scene Generation: An LLM-Driven Pipeline for 2D Game Environments](https://mlsanity.com/paper/2509.04481/) (2025)
- [Attention, not scale, drives human-AI alignment in multimodal language prediction](https://mlsanity.com/paper/2308.06035/) (2023)
- [Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs](https://mlsanity.com/paper/2508.14941/) (2025)
- [LLMs Behind the Scenes: Enabling Narrative Scene Illustration](https://mlsanity.com/paper/2509.22940/) (2025)
- [Empirical Prompt Engineering for Construct Identification with Large Language Models](https://mlsanity.com/paper/2512.03818/) (2025)
- [Coherence in the brain unfolds across separable temporal regimes](https://mlsanity.com/paper/2512.20481/) (2025)
- [Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models](https://mlsanity.com/paper/2607.22575/) (2026)

## Abstract (arXiv)

Humans perceive discrete events such as "restaurant visits" and "train rides" in their continuous experience. One important prerequisite for studying human event perception is the ability of researchers to quantify when one event ends and another begins. Typically, this information is derived by aggregating behavioral annotations from several observers. Here we present an alternative computational approach where event boundaries are derived using a large language model, GPT-3, instead of using human annotations. We demonstrate that GPT-3 can segment continuous narrative text into events. GPT-3-annotated events are significantly correlated with human event annotations. Furthermore, these GPT-derived annotations achieve a good approximation of the "consensus" solution (obtained by averaging across human annotations); the boundaries identified by GPT-3 are closer to the consensus, on average, than boundaries identified by individual human annotators. This finding suggests that GPT-3 provides a feasible solution for automated event annotations, and it demonstrates a further parallel between human cognition and prediction in large language models. In the future, GPT-3 may thereby help to elucidate the principles underlying human event perception.