Publications

Publications and preprints in natural language processing, scientific AI, crisis informatics, and multimodal verification.

My publications span multimodal verification, scientific and environmental NLP, crisis informatics, and domain-adapted language models. I am especially interested in work that connects model capability with grounded evidence, interpretability, and real-world decision support.

Selected Themes

  • Video and multimodal verification: grounding inconsistencies between generated or retrieved text and visual evidence.
  • Domain-specific LLMs: adapting and evaluating language models for chemistry, scientific corpora, and environmental review.
  • Crisis and misinformation modeling: using NLP and multimodal features to understand crisis-related social media and fake-news stance.

Publication List

2026

  1. groundinc.png
    GroundInc: Grounding Inconsistencies for Video Caption Verification
    Shivam Sharma, Y. Kementchedjhieva, and I. Gurevych
    Under Review, EMNLP, 2026

2024

  1. Exploring the benefits of domain-pretraining of generative large language models for chemistry
    A. Acharya, Shivam Sharma, R. Cosbey, and 3 more authors
    arXiv, 2024
    arXiv
  2. nepatec1.0.png
    Benchmarking LLMs for Environmental Review and Permitting
    R. Meyur, H. Phan, K. Hayashi, and 12 more authors
    arXiv, 2024
    arXiv
  3. rag_vs_long.png
    RAG vs. Long Context: Examining Frontier Large Language Models for Environmental Review Document Comprehension
    H. Phan, A. Acharya, S. Chaturvedi, and 8 more authors
    arXiv, 2024
    PDF

2022

  1. bigscience_workshop.png
    Foundation models of scientific knowledge for chemistry: Opportunities, challenges and lessons learned
    S. Horawalavithana, E. Ayton, Shivam Sharma, and 6 more authors
    In BigScience Workshop, 2022
    HTML PDF
  2. Expert: Public benchmarks for dynamic heterogeneous academic graphs
    S. Horawalavithana, E. Ayton, A. Usenko, and 5 more authors
    arXiv, 2022
    arXiv
  3. Evaluating and explaining natural language generation with genx
    K. Duskin, Shivam Sharma, J. Y. Yun, and 2 more authors
    In DaSH, EMNLP, 2022
    PDF

2021

  1. An Evaluation of Twitter Datasets from Non-Pandemic Crises Applied to Regional COVID-19 Contexts
    Shivam Sharma and C. Buntain
    In ISCRAM, 2021
    PDF

2020

  1. Improving Classification of Crisis-Related Social Media Content via Text Augmentation and Image Analysis
    Shivam Sharma and C. Buntain
    In TREC-IS, 2020
    PDF

2018

  1. iit_paper.png
    Combining neural, statistical and external features for fake news stance identification
    G. Bhatt, A. Sharma, Shivam Sharma, and 3 more authors
    In MSM, The Web Conference (WWW), 2018
    PDF Code