<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2026-num2event">
    <titleInfo>
        <title>NUM2EVENT: Structured Event Inference from Numerical Time-Series</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ninghui</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Songning</namePart>
        <namePart type="family">Lai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xinan</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="family">Chu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiyan</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) have shown strong multimodal reasoning abilities, yet their understanding of purely numerical time-series remains limited. Existing approaches mainly focus on forecasting or trend description, providing little insight into the underlying events that have occurred or are unfolding within observed numerical dynamics. We study number-to-event reasoning and decoding, a task that infers interpretable and structured event hypotheses directly from numerical time-series when explicit event information is unavailable at inference time. The task focuses on aligned and plausible event semantics that help explain observed numerical dynamics. To address data scarcity and semantic alignment challenges, we propose a reasoning-aware framework that combines an agent-guided event extractor, a Hawkes-process-based synthetic data generator, and a multi-stage fine-tuning pipeline integrating a time-series encoder with a structured event decoder. The model generates intermediate reasoning steps and outputs constrained event representations. Experiments across multiple real-world domains show that our approach consistently outperforms strong LLM baselines in event-level precision and recall, demonstrating its effectiveness in bridging numerical reasoning and semantic event understanding. The code is available at https://github.com/feng1201/NUM2EVENT_IDEA</abstract>
    <identifier type="citekey">feng-etal-2026-num2event</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1536/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>32675</start>
            <end>32693</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T NUM2EVENT: Structured Event Inference from Numerical Time-Series
%A Feng, Ninghui
%A Lai, Songning
%A Chen, Xinan
%A Chu, Zheng
%A Qi, Yiyan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F feng-etal-2026-num2event
%X Large language models (LLMs) have shown strong multimodal reasoning abilities, yet their understanding of purely numerical time-series remains limited. Existing approaches mainly focus on forecasting or trend description, providing little insight into the underlying events that have occurred or are unfolding within observed numerical dynamics. We study number-to-event reasoning and decoding, a task that infers interpretable and structured event hypotheses directly from numerical time-series when explicit event information is unavailable at inference time. The task focuses on aligned and plausible event semantics that help explain observed numerical dynamics. To address data scarcity and semantic alignment challenges, we propose a reasoning-aware framework that combines an agent-guided event extractor, a Hawkes-process-based synthetic data generator, and a multi-stage fine-tuning pipeline integrating a time-series encoder with a structured event decoder. The model generates intermediate reasoning steps and outputs constrained event representations. Experiments across multiple real-world domains show that our approach consistently outperforms strong LLM baselines in event-level precision and recall, demonstrating its effectiveness in bridging numerical reasoning and semantic event understanding. The code is available at https://github.com/feng1201/NUM2EVENT_IDEA
%U https://aclanthology.org/2026.findings-emnlp.1536/
%P 32675-32693

Markdown (Informal)

[NUM2EVENT: Structured Event Inference from Numerical Time-Series](https://aclanthology.org/2026.findings-emnlp.1536/) (Feng et al., Findings 2026)

• NUM2EVENT: Structured Event Inference from Numerical Time-Series (Feng et al., Findings 2026)

ACL

• Ninghui Feng, Songning Lai, Xinan Chen, Zheng Chu, and Yiyan Qi. 2026. NUM2EVENT: Structured Event Inference from Numerical Time-Series. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 32675–32693, Budapest, Hungary. Association for Computational Linguistics.