@inproceedings{lyu-etal-2025-facttrack,
title = "{F}act{T}rack: Time-Aware World State Tracking in Story Outlines",
author = "Lyu, Zhiheng and
Yang, Kevin and
Kong, Lingpeng and
Klein, Dan",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.144/",
doi = "10.18653/v1/2025.naacl-long.144",
pages = "2825--2848",
ISBN = "979-8-89176-189-6",
abstract = "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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lyu-etal-2025-facttrack">
<titleInfo>
<title>FactTrack: Time-Aware World State Tracking in Story Outlines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiheng</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingpeng</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">lyu-etal-2025-facttrack</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.144</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.144/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2825</start>
<end>2848</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FactTrack: Time-Aware World State Tracking in Story Outlines
%A Lyu, Zhiheng
%A Yang, Kevin
%A Kong, Lingpeng
%A Klein, Dan
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F lyu-etal-2025-facttrack
%X 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.
%R 10.18653/v1/2025.naacl-long.144
%U https://aclanthology.org/2025.naacl-long.144/
%U https://doi.org/10.18653/v1/2025.naacl-long.144
%P 2825-2848
Markdown (Informal)
[FactTrack: Time-Aware World State Tracking in Story Outlines](https://aclanthology.org/2025.naacl-long.144/) (Lyu et al., NAACL 2025)
ACL
- Zhiheng Lyu, Kevin Yang, Lingpeng Kong, and Dan Klein. 2025. FactTrack: Time-Aware World State Tracking in Story Outlines. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2825–2848, Albuquerque, New Mexico. Association for Computational Linguistics.