ArticleBehavior research methods2025
Large language models can segment narrative events similarly to humans.
Article in Behavior research methods, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 17 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
17 citing papers in PubMed.
- Disentangling interaction and bias effects in opinion dynamics of large language models.Nature communications · 2026Article
- Article
- Hippocampo-neocortical interaction as compressive retrieval-augmented generation.Nature communications · 2026Article
- Interactive narratives reveal the personalizing effect of agency on episodic memory.Nature communications · 2026Article
- Natural language processing captures memory content associated with shared neural patterns at encoding and retrieval.Communications psychology · 2026Article
- Classification of decomposed neural data in memory networks and LLM-based stimuli processing.Brain imaging and behavior · 2026Article
- Neural Signatures of Engagement and Event Segmentation during Story Listening in Background Noise.eNeuro · 2026Article
- Article
- Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models.Proceedings of machine learning research · 2026Article
- Event segmentation applications in large language model enabled automated recall assessments.Communications psychology · 2025Article
- Temporal propagation of neural state boundaries in naturalistic context.Cerebral cortex (New York, N.Y. : 1991) · 2025Article
- Neural dynamics of spontaneous memory recall and future thinking in the continuous flow of thoughts.Nature communications · 2025Article
- Fast-timescale hippocampal processes bridge between slowly unfurling neocortical states during memory search.bioRxiv : the preprint server for biology · 2025Article
- Large-scale study of human memory for meaningful narratives.Learning & memory (Cold Spring Harbor, N.Y.) · 2025Article
- The "Naturalistic Free Recall" dataset: four stories, hundreds of participants, and high-fidelity transcriptions.Scientific data · 2024Article
- Collective events and individual affect shape autobiographical memory.Proceedings of the National Academy of Sciences of the United States of America · 2023Article
- Language-agnostic, Automated Assessment of Listeners' Speech Recall Using Large Language Models.Trends in hearingArticle
Corrections and comments
- Update of
Authors and funding
4 authors.
Funding
Abstract
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.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.