{
  "abstract": "Image captioning models generate coherent descriptions that are linguistically fluent. Because of similarity-based training objectives, generated captions are repetitive. In most techniques that aim to generate diverse, human-like captions, strong language priors lead to visually unsupported entities. This paper proposes Confidence-Calibrated Contextual Control for Diverse and Faithful Image Captions (C4DF), a decoding-time framework that reduces hallucinated objects while maintaining diversity and fluency. Image-specific pseudo-context adaptively suppresses tokens guided by confidence calibration. Prefix token conditioning controls diversity, while confidence-calibrated token suppression during decoding improves grounding. Experiments on the benchmark dataset demonstrate an improvement in CIDEr from 46.96 to 51.69 while reducing the noun non-context rate by 9.48%. Qualitative analysis confirms this balance between diversity and faithfulness without compromising on linguistic fluency.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Engineering, MIT Academy of Engineering, Affiliated to Savitribai Phule Pune University, Pune, India."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Sharmila Kharat"
    },
    {
      "affs": [
        0
      ],
      "name": "Sunita Barve"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4c276z4p50bp0.bib",
  "cited_by": 0,
  "doi": "10.1016/j.mex.2026.104199",
  "fulltext_url": "https://europepmc.org/articles/PMC13694804",
  "id": "4c276z4p50bp0",
  "issns": [
    "2215-0161"
  ],
  "landing_url": "https://europepmc.org/article/MED/42926827",
  "language": "eng",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1707|Multimodal Machine Learning Applications"
    ]
  ],
  "openalex": "W7221344348",
  "pdf_url": "https://europepmc.org/articles/PMC13694804?pdf=render",
  "pmcid": "PMC13694804",
  "pmid": "42926827",
  "published": "2026-10-10",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4c276z4p50bp0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:18Z",
      "native_id": "MED:42926827",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42926827"
    }
  ],
  "subjects": [],
  "title": "C4DF: confidence calibrated contextual control for diverse and faithful image captioning.",
  "title_text": "C4DF: confidence calibrated contextual control for diverse and faithful image captioning.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:21:18Z",
  "url": "https://research.draconitic.com/paper/4c276z4p50bp0",
  "venue": "MethodsX",
  "versions": []
}