Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

CrisiLangs: A Multilingual Resource for Crisis Warning Generation

Giacomo Gonella, Stefano Menini, Marco Guerini

Published

Oct 22, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Oct 22, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Communicating with the public during an emergency entails issuing warning messages promptly. In Europe, it often requires producing them in more than one language. Recent work has shown that language models can be trained to generate warning messages as a crisis unfolds, but the available data covers only English. To fill this gap, we present CrisiLangs, a multilingual extension of CrisiText (an English dataset of crisis events paired with warning messages written according to expert communication guidelines) to Italian, Bulgarian, German, and Greek. Expert native speakers translated the warning messages of 1,000 events drawn from 411 scenarios, for a total of 5,000 event-message pairs across five languages. We test the resource to fine-tune a multilingual model on all five languages jointly, with and without the emergency guidelines in the prompt, and compare it with a zero-shot baseline. The fine-tuned models outperform the baseline on ROUGE-L, BLEU and BERTScore in every language and configuration. In a human preference study, low decoding temperatures receive the most preferences in all five languages and in both configurations, while the effect of the guidelines varies by language.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Pairwise Preference

Directly usable for protocol triage.

"Communicating with the public during an emergency entails issuing warning messages promptly."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Communicating with the public during an emergency entails issuing warning messages promptly."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Communicating with the public during an emergency entails issuing warning messages promptly."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Communicating with the public during an emergency entails issuing warning messages promptly."

Reported Metrics

strong

Bleu, Rouge, Bertscore

Useful for evaluation criteria comparison.

"The fine-tuned models outperform the baseline on ROUGE-L, BLEU and BERTScore in every language and configuration."

Rater Population

strong

Domain Experts

Helpful for staffing comparability.

"To fill this gap, we present CrisiLangs, a multilingual extension of CrisiText (an English dataset of crisis events paired with warning messages written according to expert communication guidelines) to Italian, Bulgarian, German, and Greek."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

bleurougebertscore
Human feedback details
Uses human feedback
Yes
Feedback types
Pairwise Preference
Rater population
Domain Experts
Expertise required
Multilingual
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Communicating with the public during an emergency entails issuing warning messages promptly.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Communicating with the public during an emergency entails issuing warning messages promptly.
  • In Europe, it often requires producing them in more than one language.
  • Recent work has shown that language models can be trained to generate warning messages as a crisis unfolds, but the available data covers only English.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Pairwise preference evaluation Expert verification evaluation

Contribution summary

  • To fill this gap, we present CrisiLangs, a multilingual extension of CrisiText (an English dataset of crisis events paired with warning messages written according to expert communication guidelines) to Italian, Bulgarian, German, and Greek.
  • The fine-tuned models outperform the baseline on ROUGE-L, BLEU and BERTScore in every language and configuration.
  • In a human preference study, low decoding temperatures receive the most preferences in all five languages and in both configurations, while the effect of the guidelines varies by language.

Why it matters for eval

  • In a human preference study, low decoding temperatures receive the most preferences in all five languages and in both configurations, while the effect of the guidelines varies by language.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: bleu, rouge, bertscore