{
  "annotation_id": "68267ce7-772e-415a-a023-858eb4e2c9ca",
  "date_created": "2026-02-17T05:53:08.710000Z",
  "date_modified": "2026-02-17T05:53:08.710000Z",
  "file_hash": "66d1d81852bc0723b6421e5d666dbdc7089d22912767c21309c8a61e81b6390d",
  "private": false,
  "record": {
    "abstract": "Current Natural Language Inference (NLI) systems primarily operate at the sentence level, providing black-box decisions that lack explanatory power. While atomic-level NLI offers a promising alternative by decomposing hypotheses into individual facts, we demonstrate that the conventional assumption that a hypothesis is entailed only when all its atomic facts are entailed fails in practice due to models\u0027 poor performance on fine-grained reasoning. Our analysis reveals that existing models perform substantially worse on atomic level inference compared to sentence level tasks. To address this limitation, we introduce Atomic-SNLI, a novel dataset constructed by decomposing SNLI and enriching it with carefully curated atomic level examples through linguistically informed generation strategies. Experimental results demonstrate that models fine-tuned on Atomic-SNLI achieve significant improvements in atomic reasoning capabilities while maintaining strong sentence level performance, enabling both accurate judgements and transparent, explainable results at the fact level.",
    "arxiv_id": "2601.06528",
    "authors": [
      "Minghui Huang"
    ],
    "categories": [
      "cs.CL",
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Atomic-SNLI: Fine-Grained Natural Language Inference through Atomic Fact Decomposition",
    "url": "https://arxiv.org/abs/2601.06528",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "3a1d8669-d29d-452b-a50d-8e5715becae9",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}