arXiv Computation and Language
Language Models Have Interpretable Narrative Mechanisms
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Computation and Language
Oct 1
Evaluating Whether LLMs Can Reliably Connect the DOTs?
arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mi...
arXiv Computation and Language
Sep 11
Characterizing Narrative Content in Web-scale LLM Pretraining Data
The paper presents a detailed examination of narrative elements—agency, setting, and events—within the Dolma web-scale pretraining corpus. Using a framework of 11 interpretable dimensions, the authors hand‑annotated 400 passages, expanded this to a 25,000‑passage LLM‑labeled dataset, and trained NarraBERT models to predict narrative features across 13 million passages, producing the NarraDolma dataset. The study reveals that narrative structure is measurable at scale and that narrative qualities vary unevenly across different data sources, topics, and formats, highlighting gaps in current data curation practices.
arXiv AI
Jun 29
Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing
arXiv:2606. 27598v1 Announce Type: cross Abstract: Ultra-fine entity typing (UFET) assigns highly specific types to entity mentions, but current approaches struggle with types in the long tail.
arXiv AI
Jun 18
Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey
arXiv:2602. 15851v2 Announce Type: replace-cross Abstract: Applications of narrative theories using large language models (LLMs) deliver promising methods in automatic story generation and understanding tasks.
arXiv Computation and Language
5d ago
Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension
The study examines how varying the context window size of GPT‑2 affects its alignment with human reading-time data. A U‑shaped relationship is found: very short windows (<20 tokens) capture local memory limits, while larger windows (500–1,000 tokens) provide the best overall fit. Counterfactual experiments that disrupt cross‑sentential coreference chains show that these long‑range coreference relations are crucial for the improved fit of larger context windows.
arXiv AI
Jun 17
Do Large Language Models Always Tell The Same Stories?
arXiv:2606. 17350v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the generation of high-quality prose, yet the question of whether these models are capable of generating diverse outputs remains contested.