International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1713617

1713617PublishedVol 9 · Issue 7

Investigating Data Leakage?Induced Over-Confidence and Explanation Faithfulness in Transformer-Based Text and Audio Models

Rahul Vakiti

Subject area: Science,Engineering and Technology  ·  Area of research: Artificial Intelligence / Machine Learning

DOI: https://doi.org/10.64388/IREV9I7-1713617

Abstract

Transformer-based models now sit at the center of modern artificial intelligence, powering systems that read, listen, respond, and increasingly act on behalf of humans. From large-scale language models to voice-driven assistants, these systems exhibit a level of fluency and responsiveness that would have seemed implausible only a few years ago. Their success has been driven largely by scale Larger models, larger datasets, and longer training regimes resulting in impressive performance across text and audio tasks.

How to cite this paper

Rahul Vakiti "Investigating Data Leakage?Induced Over-Confidence and Explanation Faithfulness in Transformer-Based Text and Audio Models" Iconic Research And Engineering Journals Volume 9 Issue 7 2026 Page 1481-1493 https://doi.org/10.64388/IREV9I7-1713617
Rahul Vakiti "Investigating Data Leakage?Induced Over-Confidence and Explanation Faithfulness in Transformer-Based Text and Audio Models" Iconic Research And Engineering Journals, vol. 9, no. 7, Jan. 2026, doi: https://doi.org/10.64388/IREV9I7-1713617
Rahul Vakiti (2026). Investigating Data Leakage?Induced Over-Confidence and Explanation Faithfulness in Transformer-Based Text and Audio Models. Iconic Research And Engineering Journals, 9(7). doi: https://doi.org/10.64388/IREV9I7-1713617
Rahul Vakiti "Investigating Data Leakage?Induced Over-Confidence and Explanation Faithfulness in Transformer-Based Text and Audio Models" Iconic Research And Engineering Journals, vol. 9, no. 7, Jan. 2026. Crossref, https://doi.org/10.64388/IREV9I7-1713617
@article{1713617,
      author = {Rahul Vakiti},
      title = {Investigating Data Leakage?Induced Over-Confidence and Explanation Faithfulness in Transformer-Based Text and Audio Models},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {7},
      pages = {1481-1493},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1713617.pdf},
      abstract = {Transformer-based models now sit at the center of modern artificial intelligence, powering systems that read, listen, respond, and increasingly act on behalf of humans. From large-scale language models to voice-driven assistants, these systems exhibit a level of fluency and responsiveness that would have seemed implausible only a few years ago. Their success has been driven largely by scale Larger models, larger datasets, and longer training regimes resulting in impressive performance across text and audio tasks.},
      month = {January},
      doi = {https://doi.org/10.64388/IREV9I7-1713617}
  }