@inproceedings{atiq-etal-2026-amrood,
title = "Amrood at {LT}4{CPR} 2026: A Unified Generate-and-Judge {LLM} Pipeline for Automatic Situation Report Generation",
author = "Atiq, Muhammad Ahsan and
Butt, Mohib Ahmad and
Shaheen, Nusrat",
editor = "Ticona, Belu and
Xia, Fei and
Lewis, William D. and
Anastasopoulos, Antonios",
booktitle = "Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.lt4cpr-1.15/",
pages = "166--176",
ISBN = "979-8-89176-450-7",
abstract = "We present nemotron-120b-sitrep, an end-to-end four-stage generate-and-judge pipeline submitted to the First Shared Task on Automatic Situation Report Generation from Crisis Social Media Data at LT4CPR 2026 (AACL-IJCNLP 2026). Powered by NVIDIA{'}s Nemotron-3 Super 120B model hosted on the NVIDIA NIM API, the pipeline tackles the acute challenges of emergency reporting (social media noise, multi-section hierarchical taxonomies, and strict tweet-to-claim evidence attribution) by decomposing generation into: (1) rule-based ingestion and noise filtering, (2) unified template-filling synthesis across an 11-section situation report (SITREP) taxonomy under strict canonical subsection and evidence-grounding constraints, (3) cross-section deduplication, granular bullet consolidation, and dual-source confidence calibration via a Senior Judge LLM, and (4) Schema v1.2 JSON assembly. On the official shared task evaluation, our system achieves an Official Primary Score of 0.5733 on the 117-cell blind test set (BERTScore F1 of 0.5984 and BLEURT of 0.5483), demonstrating consistent performance that transfers to unseen crisis types, with scores of 0.5011 on the 140-cell training benchmark and 0.5057 on the 23-cell development benchmark. We provide a detailed calamity-by-calamity analysis across disaster scenarios, full algorithmic hyperparameters, and prompt engineering specifications."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atiq-etal-2026-amrood">
<titleInfo>
<title>Amrood at LT4CPR 2026: A Unified Generate-and-Judge LLM Pipeline for Automatic Situation Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Ahsan</namePart>
<namePart type="family">Atiq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohib</namePart>
<namePart type="given">Ahmad</namePart>
<namePart type="family">Butt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nusrat</namePart>
<namePart type="family">Shaheen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response</title>
</titleInfo>
<name type="personal">
<namePart type="given">Belu</namePart>
<namePart type="family">Ticona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-450-7</identifier>
</relatedItem>
<abstract>We present nemotron-120b-sitrep, an end-to-end four-stage generate-and-judge pipeline submitted to the First Shared Task on Automatic Situation Report Generation from Crisis Social Media Data at LT4CPR 2026 (AACL-IJCNLP 2026). Powered by NVIDIA’s Nemotron-3 Super 120B model hosted on the NVIDIA NIM API, the pipeline tackles the acute challenges of emergency reporting (social media noise, multi-section hierarchical taxonomies, and strict tweet-to-claim evidence attribution) by decomposing generation into: (1) rule-based ingestion and noise filtering, (2) unified template-filling synthesis across an 11-section situation report (SITREP) taxonomy under strict canonical subsection and evidence-grounding constraints, (3) cross-section deduplication, granular bullet consolidation, and dual-source confidence calibration via a Senior Judge LLM, and (4) Schema v1.2 JSON assembly. On the official shared task evaluation, our system achieves an Official Primary Score of 0.5733 on the 117-cell blind test set (BERTScore F1 of 0.5984 and BLEURT of 0.5483), demonstrating consistent performance that transfers to unseen crisis types, with scores of 0.5011 on the 140-cell training benchmark and 0.5057 on the 23-cell development benchmark. We provide a detailed calamity-by-calamity analysis across disaster scenarios, full algorithmic hyperparameters, and prompt engineering specifications.</abstract>
<identifier type="citekey">atiq-etal-2026-amrood</identifier>
<location>
<url>https://aclanthology.org/2026.lt4cpr-1.15/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>166</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Amrood at LT4CPR 2026: A Unified Generate-and-Judge LLM Pipeline for Automatic Situation Report Generation
%A Atiq, Muhammad Ahsan
%A Butt, Mohib Ahmad
%A Shaheen, Nusrat
%Y Ticona, Belu
%Y Xia, Fei
%Y Lewis, William D.
%Y Anastasopoulos, Antonios
%S Proceedings of the First Workshop on Language Technologies for Crisis Preparedness and Response
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-450-7
%F atiq-etal-2026-amrood
%X We present nemotron-120b-sitrep, an end-to-end four-stage generate-and-judge pipeline submitted to the First Shared Task on Automatic Situation Report Generation from Crisis Social Media Data at LT4CPR 2026 (AACL-IJCNLP 2026). Powered by NVIDIA’s Nemotron-3 Super 120B model hosted on the NVIDIA NIM API, the pipeline tackles the acute challenges of emergency reporting (social media noise, multi-section hierarchical taxonomies, and strict tweet-to-claim evidence attribution) by decomposing generation into: (1) rule-based ingestion and noise filtering, (2) unified template-filling synthesis across an 11-section situation report (SITREP) taxonomy under strict canonical subsection and evidence-grounding constraints, (3) cross-section deduplication, granular bullet consolidation, and dual-source confidence calibration via a Senior Judge LLM, and (4) Schema v1.2 JSON assembly. On the official shared task evaluation, our system achieves an Official Primary Score of 0.5733 on the 117-cell blind test set (BERTScore F1 of 0.5984 and BLEURT of 0.5483), demonstrating consistent performance that transfers to unseen crisis types, with scores of 0.5011 on the 140-cell training benchmark and 0.5057 on the 23-cell development benchmark. We provide a detailed calamity-by-calamity analysis across disaster scenarios, full algorithmic hyperparameters, and prompt engineering specifications.
%U https://aclanthology.org/2026.lt4cpr-1.15/
%P 166-176
Markdown (Informal)
[Amrood at LT4CPR 2026: A Unified Generate-and-Judge LLM Pipeline for Automatic Situation Report Generation](https://aclanthology.org/2026.lt4cpr-1.15/) (Atiq et al., LT4CPR 2026)
ACL