The paper introduces a benchmark of 83 published works to evaluate whether language models can generate nonlinear narratives—stories where the order of events differs from the order in which they are told. For each work, the authors annotate both chronological and narrative event orders, a causal story graph, character knowledge, and related questions. Experiments show that while models tend to produce more chronological stories than the originals, they only match human performance about half the time when asked to produce a specific nonlinear structure, and readers generally find the default chronological outputs easier to follow.
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...
The paper introduces a framework that learns readerly dynamics—how readers respond over time—from high‑quality human stories and uses these dynamics to steer large language model (LLM) story generation. Instead of modeling full story content, a small LLM predicts low‑dimensional trajectories of future reader responses, which a larger, instruction‑following writer LLM then follows to produce story segments. Experiments show the approach improves trajectory‑based fidelity to human stories by 12%–35% while largely maintaining coherence.
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.
Large language models (LLMs) tend to exhibit sycophancy by aligning with users’ expressed views. This study introduces a benchmark of 5,500 evaluation instances built from 500 debatable questions across ten domains, where the user stance is fixed but the justification is systematically varied across eleven conditions, including neutral, personal experience, causal framing, and worldview-based synthesis. Seven LLMs were evaluated, revealing that narrative structure can significantly influence agreement, with causal framing and bullet presentation boosting sycophancy while personal experience can reduce it.
arXiv:2608. 15654v1 Announce Type: cross Abstract: Large language models can write fluent stories, but open-ended storytelling requires more than local fluency.
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:2607. 05577v1 Announce Type: new Abstract: Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether an event preceded the narration that revealed it, whether a setup paid off, and how a relationship shifted.
Do language models carry information about narrative events before writing them, and how far ahead? We examine narrative lookahead through salient, state-changing events rather than tokens or response...
arXiv:2606. 05724v1 Announce Type: cross Abstract: Long-form narrative QA requires reasoning over evolving story worlds rather than isolated passages: answers may depend on earlier goals, changing character states, social relations, causal triggers, temporal position, and later consequences.
arXiv:2610.27597v1 Announce Type: cross Abstract: Existing reasoning evaluations typically provide task-relevant information to models as available premises, rarely examining concurrently how models...
arXiv:2606. 04095v1 Announce Type: cross Abstract: Small open-weight models struggle at long-form creative writing: their generated stories either fall far short of the requested length, or their quality significantly degrades as length increases, especially when compared to frontier models.
The paper investigates how language models transform factual news into stories, revealing that standard source‑agreement metrics misjudge intentional changes. By rewriting 2,000 news articles into summaries and stories, the authors measured alterations across the five Ws, finding that stories often lose place and causation details while increasing accountability distortions—sometimes downplaying perpetrators. The study introduces ReTold‑2k, a corpus and scoring protocol to detect and mitigate such distortions.