# FACTTRACK: Time-Aware World State Tracking in Story Outlines

arXiv: https://arxiv.org/abs/2407.16347 · HTML: https://mlsanity.com/paper/2407.16347/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 7 of 7)

- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://mlsanity.com/paper/2112.07916/) (2021)
- [Re3: Generating Longer Stories With Recursive Reprompting and Revision](https://mlsanity.com/paper/2210.06774/) (2022)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [Tracking the World State with Recurrent Entity Networks](https://mlsanity.com/paper/1612.03969/) (2016)
- [Improving Pacing in Long-Form Story Planning](https://mlsanity.com/paper/2311.04459/) (2023)

## Built on by (most cited first, 6 of 6)

- [Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams](https://mlsanity.com/paper/2603.07392/) (2026)
- [From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives](https://mlsanity.com/paper/2607.00918/) (2026)
- [NARRA-Gym for Evaluating Interactive Narrative Agents](https://mlsanity.com/paper/2605.08503/) (2026)
- [When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations](https://mlsanity.com/paper/2608.15654/) (2026)
- [Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation](https://mlsanity.com/paper/2609.32401/) (2026)
- [Scaling Long-Form Story Generation via Narrative State Tracking](https://mlsanity.com/paper/2609.35759/) (2026)

## Abstract (arXiv)

While accurately detecting and correcting factual contradictions in language model outputs has become increasingly important as their capabilities improve, doing so is highly challenging. We propose a novel method, FACTTRACK, for tracking atomic facts and addressing factual contradictions. Crucially, FACTTRACK also maintains time-aware validity intervals for each fact, allowing for change over time. At a high level, FACTTRACK consists of a four-step pipeline to update a world state data structure for each new event: (1) decompose the event into directional atomic facts; (2) determine the validity interval of each atomic fact using the world state; (3) detect contradictions with existing facts in the world state; and finally (4) add new facts to the world state and update existing atomic facts. When we apply FACTTRACK to contradiction detection on structured story outlines, we find that FACTTRACK using LLaMA2-7B-Chat substantially outperforms a fair baseline using LLaMA2-7B-Chat, and achieves performance comparable to a GPT4 baseline. Moreover, when using GPT4, FACTTRACK significantly outperforms the GPT4 baseline.