{
  "abstract": "Selective classification enables a model to abstain from predictions on uncertain instances, but existing approaches typically reject them through confidence scores, predefined coverage constraints or instance-level distance measures. These approaches may overlook the collective geometric structure of difficult samples in learned representation spaces. We propose Guided Clustering-based Uncertain Learning (GCUL), a geometric-guided selective classification framework that identifies misclassified and ambiguous instances as a potential confusion attractor in the representation space. GCUL uses a three-phase procedure to initialize, cluster, and explicitly relabel this uncertain region, allowing the rejection boundary to emerge from the underlying representation geometry rather than from a prescribed rejection rate. We further derive a selectivity score and a geometric sufficient condition that characterizes when rejection can provide positive operational utility, enabling pre-deployment feasibility assessment. GCUL improves DistilBERT accuracy from 89.37 percent to 94.98 percent with less than 9 percent rejection. Beyond accuracy, our selectivity score correctly pre-detects the only dataset (GoEmotion) where all baselines fail, and controlled simulations yield 6.1 percent Type-I and 0 percent Type-II errors, validating the sufficient condition's conservatism. These results suggest that collective representation geometry provides a useful alternative perspective for selective prediction.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.29327",
  "author_total": 3,
  "authors": [
    {
      "name": "Zhongqi Fan"
    },
    {
      "name": "Tianyou Zhang"
    },
    {
      "name": "Fei Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/58fa8mqsf10h0.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.29327",
  "fulltext_url": null,
  "id": "58fa8mqsf10h0",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.29327",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Sentiment Analysis and Opinion Mining"
    ]
  ],
  "openalex": "W7214386428",
  "pdf_url": "https://arxiv.org/pdf/2609.29327",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/58fa8mqsf10h0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:21Z",
      "native_id": "2609.29327",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.29327"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning",
  "title_text": "GCUL: Ambiguity Identification in Text Emotion Classification via Cluster-Guided Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:21Z",
  "url": "https://research.draconitic.com/paper/58fa8mqsf10h0",
  "venue": "arXiv",
  "versions": []
}