Publications

Conference Papers:

• Christopher M. Homan, Flip Korn, Deepak Pandita, and Chris Welty. 2025. How Many Ratings per Item are Necessary for Reliable Significance Testing?. Manuscript submitted for review.

• Deepak Pandita, Flip Korn, Chris Welty, and Christopher M. Homan. 2026. Forest vs Tree: The (N, K) Trade-off in Reproducible ML Evaluation. To appear in the Proceedings of AAAI Conference on Artificial Intelligence.

• Deepak Pandita, Tharindu Cyril Weerasooriya, Ankit Parag Shah, Isabelle Diana May-Xin Ng, Christopher M. Homan, and Wei Wei. 2025. ProRefine: Inference-time Prompt Refinement with Textual Feedback. To appear in the AAAI-2026 Student Abstract and Poster Program and accepted at the NeurIPS 2025 Workshop on Efficient Reasoning (non-archival).

• Mandira Sawkar, Samay U. Shetty, Deepak Pandita, Tharindu Cyril Weerasooriya, and Christopher M. Homan. 2025. LPI-RIT at LeWiDi-2025: Improving Distributional Predictions via Metadata and Loss Reweighting with DisCo. In Proceedings of the 4th Workshop on Perspectivist Approaches to NLP (NLPerspectives 2025) @ EMNLP 2025, pages 196–207, Suzhou, China. Association for Computational Linguistics.

• Sujan Dutta, Deepak Pandita, Tharindu Cyril Weerasooriya, Marcos Zampieri, Christopher M. Homan, and Ashiqur R. KhudaBukhsh. 2025. ARTICLE: Annotator Reliability Through In-Context Learning. In Proceedings of AAAI Conference on Artificial Intelligence, 39(13), 14230-14237.

• Sujan Dutta, Deepak Pandita, Tharindu Cyril Weerasooriya, Marcos Zampieri, Christopher M. Homan, and Ashiqur R. KhudaBukhsh. 2025. ARTICLE: Annotator Reliability Through In-Context Learning (Student Abstract). In Proceedings of AAAI Conference on Artificial Intelligence, 39(28), 29356-29358.

• Deepak Pandita, Tharindu Cyril Weerasooriya, Sujan Dutta, Sarah K. K. Luger, Tharindu Ranasinghe, Ashiqur R. KhudaBukhsh, Marcos Zampieri, and Christopher M. Homan. 2024. Rater Cohesion and Quality from a Vicarious Perspective. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5149–5162, Miami, Florida, USA. Association for Computational Linguistics.

• Ann Marie White, Sally W. Thurston, Tanzy Love, Deepak Pandita, and Donald Harrington. Empirical Patterns in County Suicide Burdens Over Time: Do Community Features Predict the Sets of Counties Found to Have Similar Trends? In 52nd Conference of American Association of Suicidology (AAS 19), Denver, CO, 2019.

• Ann Marie White, Linxiao Bai, Christopher M. Homan, Melanie Funchess, Catherine Cerulli, Amen Ptah, Deepak Pandita, and Henry Kautz. Does Reciprocal Gratefulness in Twitter Predict Neighborhood Safety?: Comparing 911 Calls Where Users Reside or Use Social Media. In 12th International AAAI Conference on Web and Social Media (ICWSM-2018), 25-28 June, Stanford, CA.

• Girish K. Palshikar, Manoj Apte, and Deepak Pandita. Weakly Supervised Classification of Tweets for Disaster Management. In ECIR 2017 workshop on Exploitation of Social Media for Emergency Relief and Preparedness (SMERP), 9 Apr 2017, Aberdeen, Scotland.

• Girish K. Palshikar, Manoj Apte, Deepak Pandita, and Vikram Singh. 2016. Learning to Identify Subjective Sentences. In Proceedings of the 13th International Conference on Natural Language Processing, pages 239–248, Varanasi, India. NLP Association of India.

Journal Article:

• Girish K. Palshikar, Manoj Apte, and Deepak Pandita. Weakly Supervised and Online Learning of Word Models for Classification to Detect Disaster Reporting Tweets. Information Systems Frontiers (2018), Vol. 20, No. 5, pp. 949-959.

Patent

• Manoj Apte, Sachin Pawar, Girish K. Palshikar, Sriram Baskaran, Amol M. Aaeer, and Deepak Pandita. Tata Consultancy Services Ltd, 2020. System for Standardization of Goal Setting in Performance Appraisal Process. U.S. Patent 10,699,236.