Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety

Navaneeth Sangameswaran, Preetham S, Ashmiya Lenin

Published

Jul 2, 2026

Citations

0

Trust level

High

Usefulness score

75/100 (High)

Extraction confidence

80% (High)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Jul 2, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Multilingual Red Team

Should you rely on this paper?

This paper has strong direct human-feedback and evaluation protocol signal and is suitable as a primary eval pipeline reference.

Use this as a practical starting point for protocol research, then validate against the original paper.

Best use

Primary benchmark and eval reference

Use if you need

A concrete protocol example with enough signal to inform rater workflow design.

What to verify

Validate the exact study setup 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
75/100
High-confidence candidate

Use this as a primary source when designing or comparing eval protocols.

If you are doing eval pipeline work, start here

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

Abstract

We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety. It achieves state-of-the-art performance on English and multilingual prompt-safety benchmarks at roughly one-tenth the model size of current leading open guard models. The safety constitution is the organising structure of the corpus: a natural-language constitution of 46 policies and 2,940 subcategories drives synthetic data generation, with exhaustive one-to-one paired counterfactuals that hold topic and vocabulary fixed while flipping intent, a two-tier harmless design that separately targets boundary and baseline false positives (FPs), and balanced multilingual materialisation across 46 languages that treats language as a surface form appearing on both sides of the boundary rather than as an adversarial signal. Across seven prompt-safety benchmarks, HaloGuard 1.0-0.8B attains the best average F1 (90.9) of any open guard we evaluate, outperforming baselines up to 27B parameters (over 30 times larger) while holding false-positive rate (FPR) to 4.3 and false-negative rate (FNR) to 9.5. The HaloGuard 1.0-4B variant reaches average F1 of 92.1 and FPR of 3.5, spending its extra capacity on precision rather than recall. A structured adjudication of the remaining failures indicates that most apparent missed-harm cases are benchmark mislabels rather than genuine model misses. An always-on adversarial red-teaming protocol continuously hardens the guard against both content-level and agentic attacks. We release the models as open weights.

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

Red Team

Directly usable for protocol triage.

"We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety."

Quality Controls

strong

Adjudication

Calibration/adjudication style controls detected.

"A structured adjudication of the remaining failures indicates that most apparent missed-harm cases are benchmark mislabels rather than genuine model misses."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety."

Reported Metrics

strong

F1, Precision, Recall

Useful for evaluation criteria comparison.

"The HaloGuard 1.0-4B variant reaches average F1 of 92.1 and FPR of 3.5, spending its extra capacity on precision rather than recall."

Benchmarks and datasets

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

Reported metrics

f1precisionrecall
Human feedback details
Uses human feedback
Yes
Feedback types
Red Team
Rater population
Not reported
Expertise required
Multilingual
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Adjudication
Evidence quality
High
Use this page as
Primary benchmark and eval reference

Research brief

Metadata summary

We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety.

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

Key takeaways

  • We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety.
  • It achieves state-of-the-art performance on English and multilingual prompt-safety benchmarks at roughly one-tenth the model size of current leading open guard models.
  • The safety constitution is the organising structure of the corpus: a natural-language constitution of 46 policies and 2,940 subcategories drives synthetic data generation, with exhaustive one-to-one paired counterfactuals that hold topic and vocabulary fixed while flipping intent, a two-tier harmless design that separately targets boundary and baseline false positives (FPs), and balanced multilingual materialisation across 46 languages that treats language as a surface form appearing on both sides of the boundary rather than as an adversarial signal.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • 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

F1

Contribution summary

  • We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety.
  • It achieves state-of-the-art performance on English and multilingual prompt-safety benchmarks at roughly one-tenth the model size of current leading open guard models.
  • Across seven prompt-safety benchmarks, HaloGuard 1.0-0.8B attains the best average F1 (90.9) of any open guard we evaluate, outperforming baselines up to 27B parameters (over 30 times larger) while holding false-positive rate (FPR) to 4.3…

Why it matters for eval

  • We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety.
  • Across seven prompt-safety benchmarks, HaloGuard 1.0-0.8B attains the best average F1 (90.9) of any open guard we evaluate, outperforming baselines up to 27B parameters (over 30 times larger) while holding false-positive rate (FPR) to 4.3…

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Red Team

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    Detected: Adjudication

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: f1, precision, recall