SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.18495 · NeurIPS · 2024

WILDGUARD: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Yejin Choi, Allyson Ettinger, Liwei Jiang, Nathan Lambert, Seungju Han, Kavel Rao, †♡♢ Bill, Yuchen Lin, ♡♢ Dziri

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.18495.json · badge: /api/ran/2406.18495.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
allenai/wildguard canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
SafetyClassifierOutput Ran
ran on a synthesized input · constructed an object; no result was computed
allenai/wildguard/wildguard/wildguard.py
pointer only (licence: NOASSERTION) · get_code("0ffb64bc4bf237fd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/wildguard (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SafetyClassifierBase Not yet run
unverified (harvested, no recorded run)
allenai/wildguard/wildguard/wildguard.py
pointer only (licence: NOASSERTION) · get_code("e444d59b412c001a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/wildguard (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

WildGuard Not yet run
unverified (harvested, no recorded run)
allenai/wildguard/wildguard/wildguard.py
pointer only (licence: NOASSERTION) · get_code("d3b57f572769a29c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, allenai/wildguard (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce WILDGUARD-an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal rate. Together, WILDGUARD serves the increasing needs for automatic safety moderation and evaluation of LLM interactions, providing a one-stop tool with enhanced accuracy and broad coverage across 13 risk categories. While existing open moderation tools such as Llama-Guard2 [16] score reasonably well in classifying straightforward model interactions, they lag far behind a prompted GPT-4, especially in identifying adversarial jailbreaks and in evaluating models' refusals, a key measure for evaluating safety behaviors in model responses. To address these challenges, we construct WILDGUARDMIX, a large-scale and carefully balanced multi-task safety moderation dataset with 92K labeled examples that cover vanilla (direct) prompts and adversarial jailbreaks, paired with various refusal and compliance responses. WILDGUARDMIX is a combination of WILDGUARDTRAIN, the training data of WILDGUARD, and WILDGUARDTEST, a high-quality human-annotated moderation test set with 5K labeled items covering broad risk scenarios. Through extensive evaluations on WILDGUARDTEST and ten existing public benchmarks, we show that WILDGUARD establishes state-of-the-art performance in open-source safety moderation across all the three tasks compared to ten strong existing open-source moderation models (e.g., up to 26.4% improvement on refusal detection). Importantly, WILDGUARD matches and sometimes exceeds GPT-4 performance (e.g., up to 3.9% improvement on prompt harmfulness identification). WILDGUARD serves as a highly effective safety moderator in an LLM interface, reducing the success rate of jailbreak attacks from 79.8% to 2.4%.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.18495")
get_code_for_paper("2406.18495")
have("2406.18495")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.18495.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.18495.svg)](https://syntology.ai/paper/2406.18495)

Connect an agent — have() is free.