Anurag Acharya, PhD

Email: anurag [dot] acharya [at] pnnl [dot] gov | Twitter: @anuragach

I am a Research Scientist at Pacific Northwest National Laboratory (PNNL). Earlier, he was an Adjunct Faculty at FIU's Knight Foundation School of Computing and Information Sciences.

Google Scholar

Featured: See my recenly-released benchmark, NuclearQA, a benchmark for LLMs for the nuclear domain. [paper] [git]

Research Interests

My research interests are in the broad fields of natural language processing and computational linguistics, and cultural element in AI. I am also deeply interested in commonsense reasoning, ai ethics and bias, and ways to build safe and trustworthy AI. I also actively involved in the fields of Large Langugage Models (LLMs), Retriever-Augmented Language Models (RALMs), and reasoning.

Short Bio

I received my PhD in Computer Science from Florida International University (FIU) in 2022 under the supervision of Professor Mark A. Finlayson. During my PhD, I did an internship at PNNL, and started as an Adjunct Faculty at FIU towards the end of my PhD, continuing on until Spring 2023. I received my MS in Computer Science from FIU in 2021. Before attending FIU, I had a BE in Computer Engineering and a BA in English and Political Science from Tribhuvan University.

Projects

Mega-AI: Foundation Models for Science and Security, October 2022 - present

Mega AI seeks to develop massive-scale, self-supervised, multimodal foundation models of scientific knowledge capable of general-purpose inferences to enable reasoning with existing knowledge and discovery of new knowledge across science and security domains.
Detecting Misinformation Narratives in Social Media, October 2022 - present

Extracting and graphically representing mis/disinformation micronarratives from social media surrounding COVID-19.
EXPERT: AI-driven Analytics for Nonproliferation Monitoring, October 2022 - October 2023

Usable and explainable models for global-scale, cross-lingual proliferation expertise identification and forecasting

Publications

[Book Chapter (In press)] Saldanha E., Acharya A., Ocal, M., Glenski M., & Volkova, S. (2022) “Detecting and Summarizing Narratives in the Information Environment: A Case Study of Misinformation and Disinformation Campaigns”. Detecting Online Propaganda and Misinformation.
[Conference Paper] Yarlott, W. V. H., Ochoa, A., Acharya, A., Bobrow, L., Castro-Estrada, D., Gomez, D., Zheng, J., McDonald, D., Miller, C. & Finlayson, M. A. (2021). “Finding Trolls Under Bridges: Preliminary Work on a Motif Detector”. Advances in Cognitive Systems. Virtual Conference
[Citable Abstract] Yarlott, W. V. H., Ochoa, A., Acharya, A., Bobrow, L., Castro-Estrada, D., Gomez, D., Zheng, J., McDonald, D., Miller, C. & Finlayson, M. A. (2021). “Motif Frequency and its Relation to Genre”. Literature & Culture and/as Intelligent Systems. Virtual Workshop
[Workshop Paper] Acharya, A., Talamadupula, K., & Finlayson, M. A. (2021). “Towards an Atlas of Cultural Commonsense for Machine Reasoning.” Workshop on Common Sense Knowledge Graphs (CSKGs), The Thirty-Fifth AAAI Conference on Artificial Intelligence. Virtual Conference
[Conference Paper] KC, K., Acharya, A., Acharya, A., & Shrestha, S. (2021). “Transfer Learned Mobilenets with shrinking hyperparameters for classifying Covid-19 based on X-ray images”. Advanced Engineering and ICT-Convergence Proceedings. Vol 4, No. 2. Virtual Conference

Preprints

Acharya, A., Sharma, S., Cosbey, R.J., Subramanian, M., & Glenski, M. F. “AISLE: Artificial Intelligence from Scientific Literature". Under review at LREC-COLING 2024.
Yarlott, W. V. H., Acharya, A., Castro-Estrada, D., Gomez, D., & Finlayson, M. A. “GOLEM: GOld standard for Learning and Evaluation of Motifs”. Under review at LREC-COLING 2024.
Munikoti, S., Acharya, A., Wagle, S., & Horawalavithana, Y. S. “Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning”. Under review at a NeurIPS 2023 Workshop.
Acharya, A., Munikoti, S., Wagle, S., & Horawalavithana, Y. S. “NuclearQA: A Human-Made Benchmark for Language Models for the Nuclear Domain”. Preprint, expected submission to ACL Rolling Review.
Munikoti, S., Acharya, A., Wagle, S., & Horawalavithana, Y. S. “ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science”. Preprint, expected submission to ACL Rolling Review
Wagle, S., Munikoti, S., Acharya, A., & Horawalavithana, Y. S. “Empirical evaluation of Uncertainty Quantification in Retrieval-Augmented Language Models for Science”. Preprint, expected submission to ACL Rolling Review

Talks, Seminars, and Presentations

Panel — Acharya, A. (Lead), Saldanha, E. G., & Horawalavithana, Y. S. “Towards a more ethical and trustworthy AI”, Pacific Northwest National Laboratory (PNNL). August 2023. Organized in absentia due to illness.
Conference Presentation — Acharya, A. Saldanha, E. G. (Presenter) “Detecting and studying narratives in text”, Pacific Northwest National Laboratory (PNNL). August 2023.
Conference Presentation — Wagle, S. (Presenter) , Sharma, S., Munikoti, S., Acharya, A., Briseno, D. N., Horawalavithana, Y. S. “Towards Trustworthy Natural Language Reasoning: Uncertainty Estimation in Large Language Models with Human-AI Collaboration”, Pacific Northwest National Laboratory (PNNL). August 2023.
Conference Presentation — Sharma, S. (Presenter), Acharya, A., Cosbey, R.J., Subramanian, M., & Glenski, M.F. “CHEMSAI: CHEmistry-focused Multimodal Scalable AI." PNNL. August 2023.
Invited Talk — “Integrating Cultural Knowledge into Artificially Intelligent Systems”, Pacific Northwest National Laboratory (PNNL). August 2022
Conference Presentation — Acharya, A. (Presenter), Ocal, M., Glenski, M. F., & Saldanha, E. G. “Extracting Narrative Components from Tweets”, Research Symposium, PNNL. July 2020
Invited Panel — “What is AI and What is it Good For?”, Miami-Dade College, Miami, FL. February 2020
Invited Panel — “The Future of AI”, Cognitive Science Society, Florida International University. November 2019

Advisees

Caleb Stam, Undergraduate Research Intern, Jun 2023 – present.
Diego Castro, Undergraduate Research Assistant, Feb 2020 – April 2022
Shreeja Dahal, Undergraduate Research Intern, May – Aug 2021

Other Professional Activities (Service)

Judge – “FIU Undergraduate Research Conference 2022”. Florida International University. April 2022.
Session Chair – “Ninth Advances in Cognitive Systems (ACS) Conference”, Virtual Conference. November 2021.
Member, Organizing Committee – “ComSciCon Miami 2021 – The Communicating Science workshop for graduate students”, Miami, FL. October 2021.
Reviewer – IEEE Transactions on Artificial Intelligence, Humanities & Social Sciences Communications Journal, Conference on Neural Information Processing Systems
Professional Member – Association for the Advancement of Artificial Intelligence (AAAI), Association for Computational Linguistics (ACL), Association for Computing Machinery (ACM)

Languages

Nepali Native Language
English Native Proficiency
Hindi Minimum Professional Proficiency
Urdu Spoken only, Minimum Professional Proficiency
French Elementary Proficiency

~~~

Last Updated 30^th October 2023