AN
ENT-00002949 · Dataset

Adversarial NLI

Adversarial NLI is a dataset associated with Facebook AI Research / UNC / NYU, classified in LXKeys.world as Language / Training Dataset.

Level V PersistentActiveDocumented
Human record

Overview

Adversarial NLI is a documented language dataset or benchmark. It is recorded as adversarial natural language inference benchmark, supporting evaluation or training for question answering, reasoning, dialogue, classification, translation or multilingual language understanding.

Timeline

  1. 2020Initial dataset release

    Adversarial NLI entered the documented public record in 2020. This event is retained at the precision supported by the Entry’s reviewed source history.

Capabilities

Dataset referenceBenchmark or training-data contextTask-level documentationModel evaluation supportSource-based traceability

Known limitations

Dataset coverage, licensing, annotation quality and benchmark relevance depend on the source version and use context.Performance claims should be assessed through models evaluated on the dataset rather than inferred from the dataset alone.
Technical and structured detail

Technical description

Structured LXKeys.world registry record for Adversarial NLI. Entity type: Dataset; classification: Language / Training Dataset; creator/organization context: Facebook AI Research / UNC / NYU. Canonical source anchor: https://github.com/facebookresearch/anli. The record tracks source authority, first public appearance, timeline, capabilities, limitations, registry status and graph relationships. Automatic refresh is limited to sources explicitly classified as OFFICIAL and enabled for updates; documentary and research references remain non-authoritative unless reviewed.

Controlled tags

DatasetNLPBenchmarkLanguage Understanding
Relationship graph

Adversarial NLI

Open in full graph
Adversarial NLI
Associated organizationOutgoing
Facebook AI Research / UNC / NYU

Facebook AI Research / UNC / NYU is the organization, project community or institutional context associated with Adversarial NLI.

Domain contextOutgoing
Language model evaluation and NLP data

Adversarial NLI belongs to the Language model evaluation and NLP data layer of the intelligent-entity registry.

Machine readable layer

Structured entry data for human tools, AI systems and machine clients.

{
    "@context": [
        "https://schema.org",
        {
            "lxw": "https://lxkeys.world/schema/"
        }
    ],
    "@type": "Thing",
    "identifier": "ENT-00002949",
    "name": "Adversarial NLI",
    "alternateName": [],
    "additionalType": {
        "category": "Data and Evaluation",
        "type": "Dataset",
        "subtype": "",
        "lxkeysEntity": false
    },
    "description": "Adversarial NLI is a dataset associated with Facebook AI Research / UNC / NYU, classified in LXKeys.world as Language / Training Dataset.",
    "creator": "Facebook AI Research / UNC / NYU",
    "url": "https://lxkeys.world/entry.php?id=ENT-00002949&lang=en",
    "sameAs": "https://github.com/facebookresearch/anli",
    "image": "",
    "lxkeysWorld": {
        "worldId": "ENT-00002949",
        "kind": "Data and Evaluation",
        "type": "Dataset",
        "subtype": "",
        "classification": "Language / Training Dataset",
        "organization": "Facebook AI Research / UNC / NYU",
        "originContext": "Language model evaluation and NLP data",
        "firstPublicAppearance": "2020",
        "currentStatus": "Active",
        "documentationStatus": "Documented",
        "documentationIndex": {
            "total": 82,
            "documentation": 25,
            "evidence": 13,
            "structure": 25,
            "relationships": 19,
            "level": "Level V Persistent"
        },
        "lxCalendarium": {
            "start_date_utc": "2023-04-01",
            "created_utc": "2026-06-17T01:48:33+00:00",
            "created_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4",
            "updated_utc": "2026-06-17T01:48:33+00:00",
            "updated_dypclt": "D-0 Y-2 P-3 C-3 L-22 T-4"
        },
        "facts": [],
        "capabilities": [
            "Dataset reference",
            "Benchmark or training-data context",
            "Task-level documentation",
            "Model evaluation support",
            "Source-based traceability"
        ],
        "limitations": [
            "Dataset coverage, licensing, annotation quality and benchmark relevance depend on the source version and use context.",
            "Performance claims should be assessed through models evaluated on the dataset rather than inferred from the dataset alone."
        ],
        "tags": [
            "Dataset",
            "NLP",
            "Benchmark",
            "Language Understanding"
        ],
        "timeline": [
            {
                "date": "2020",
                "title": "Initial dataset release",
                "description": "Adversarial NLI entered the documented public record in 2020. This event is retained at the precision supported by the Entry’s reviewed source history.",
                "source_url": "https://github.com/facebookresearch/anli",
                "verification_status": "source_backed_curated_baseline"
            }
        ],
        "relationships": [
            {
                "target": "Facebook AI Research / UNC / NYU",
                "type": "Associated organization",
                "description": "Facebook AI Research / UNC / NYU is the organization, project community or institutional context associated with Adversarial NLI.",
                "evidence_level": "documentary"
            },
            {
                "target": "Language model evaluation and NLP data",
                "type": "Domain context",
                "description": "Adversarial NLI belongs to the Language model evaluation and NLP data layer of the intelligent-entity registry.",
                "evidence_level": "documentary"
            }
        ],
        "sources": [
            {
                "label": "Official or reference source",
                "url": "https://github.com/facebookresearch/anli",
                "source_type": "Primary / Reference Source",
                "verification_status": "verified",
                "authority": "TRUSTED_PRIMARY",
                "role": "code_repository",
                "update_enabled": false,
                "authority_basis": "curated-corpus-refresh-2026-09-08"
            }
        ],
        "canonical": [],
        "imageMeta": []
    }
}
Proofs

Contribute to this record

Submit a source, correction or comment. Public changes remain moderated.

Submit proof or comment

Approved comments

No approved public comment yet.