{
  "abstract": "Contextual priors improve neural-to-language decoding by reshaping candidate scores. However, confidence is read from the same reshaped scores, so the errors a prior leaves behind can become more confident with no change in accuracy to reveal it. We study how a prior shapes confidence in speech retrieval on MEG-MASC and MOUS using local decoding scores, a contextual prior combined by additive shallow fusion, and the fused top-two margin as confidence. Among initially incorrect predictions, we find a confidence-ordering reversal: a larger margin makes a repair more likely when the correct candidate starts near the top of the local ranking, but less likely when it starts lower. On MEG-MASC, pooled correctness AUROC is 0.87, yet AUROC separating repairs from residual errors falls from 0.70 at initial ranks 2-3 to 0.39 at ranks 21-50. Errors starting beyond rank 20, inside the reversed region, make up 46.6% of all post-fusion errors. We propose a score-level account: a repair must first close the correct candidate's initial deficit, limiting its final margin, whereas a residual error can build a large margin between two incorrect candidates. A causal intervention that changes only the fusion weight moves the reversal to deeper ranks as predicted. Under a word-level LM prior, it keeps moving after accuracy gain peaks, so a weight chosen for accuracy does not settle confidence. Reading local and prior scores separately improves selective decoding: the decoder answers on 74.5% of windows instead of 56.7%, while 92% of output sets still contain the correct candidate. Confidence after contextual fusion should retain the local and contextual evidence behind each prediction, not just the fused scores. Project website: https://confidencereversal.github.io/; Code: https://github.com/AmadeusFake/NeuDecodingConfReversal",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.08229",
  "author_total": 2,
  "authors": [
    {
      "name": "Xinyu Zhang"
    },
    {
      "name": "Sichao Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a14v0fzps8ngr.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.08229",
  "fulltext_url": null,
  "id": "a14v0fzps8ngr",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.08229",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.IR"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "1702|Speech Recognition and Synthesis"
    ]
  ],
  "openalex": "W7220937681",
  "pdf_url": "https://arxiv.org/pdf/2610.08229",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/a14v0fzps8ngr.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:27Z",
      "native_id": "2610.08229",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.08229"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "Confidence-Ordering Reversal under Contextual Priors in Neural Decoding",
  "title_text": "Confidence-Ordering Reversal under Contextual Priors in Neural Decoding",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:27Z",
  "url": "https://research.draconitic.com/paper/a14v0fzps8ngr",
  "venue": "arXiv",
  "versions": []
}