1. GEO: Generative Engine Optimization
    Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik R Narasimhan, and 1 more author
    arXiv preprint arXiv:2311.09735, 2023
  2. Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
    Shashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, and 2 more authors
    arXiv preprint arXiv:2311.04892, 2023
  3. QualEval: Qualitative Evaluation for Model Improvement
    Vishvak Murahari*, Ameet Deshpande*, Peter Clark, Tanmay Rajpurohit, Ashish Sabharwal, and 2 more authors
    arXiv preprint arXiv:2311.02807, 2023
  4. Distraction-free Embeddings for Robust VQA
    Atharvan Dogra, Deeksha Varshney, Ashwin Kalyan, Ameet Deshpande, and Neeraj Kumar
    arXiv preprint arXiv:2309.00133, 2023
  5. InstructEval: Systematic Evaluation of Instruction Selection Methods
    Anirudh Ajith, Chris Pan, Mengzhou Xia, Ameet Deshpande, and Karthik Narasimhan
    arXiv preprint arXiv:2307.00259, 2023
  6. Anthropomorphization of AI: Opportunities and Risks
    Ameet Deshpande, Tanmay Rajpurohit, Karthik Narasimhan, and Ashwin Kalyan
    arXiv preprint arXiv:2305.14784, 2023
  7. C-STS: Conditional Semantic Textual Similarity
    Ameet Deshpande*, Carlos E Jimenez*, Howard Chen, Vishvak Murahari, Victoria Graf, and 4 more authors
    EMNLP, 2023
  8. Toxicity in ChatGPT: Analyzing Persona-assigned Language Models
    Ameet Deshpande*, Vishvak Murahari*, Tanmay Rajpurohit, Ashwin Kalyan, and Karthik Narasimhan
    EMNLP Findings, 2023
  9. MUX-PLMs: Pre-training Language Models with Data Multiplexing
    Vishvak Murahari, Ameet Deshpande, Carlos E Jimenez, Izhak Shafran, Mingqiu Wang, and 2 more authors
    EMNLP Findings, 2023
  10. SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification
    Pranjal Aggarwal, Ameet Deshpande, and Karthik Narasimhan
    arXiv preprint arXiv:2301.11309, 2023


  1. When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer
    Ameet Deshpande, Partha Talukdar, and Karthik Narasimhan
    In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
  2. Semantic supervision: Enabling generalization over output spaces
    Austin W Hanjie*, Ameet Deshpande*, and Karthik Narasimhan
    arXiv preprint arXiv:2202.13100, 2022
  3. SPARTAN: Sparse Hierarchical Memory for Parameter-Efficient Transformers
    Ameet Deshpande, Md Arafat Sultan, Anthony Ferritto, Ashwin Kalyan, Karthik Narasimhan, and 1 more author
    arXiv preprint arXiv:2211.16634, 2022
  4. ALIGN-MLM: Word Embedding Alignment is Crucial for Multilingual Pre-training
    Henry Tang, Ameet Deshpande, and Karthik Narasimhan
    arXiv preprint arXiv:2211.08547, 2022


  1. Guiding Attention for Self-Supervised Learning with Transformers
    Ameet Deshpande, and Karthik Narasimhan
    In Findings of the Association for Computational Linguistics: EMNLP 2020, 2020
  2. Evaluating a generative adversarial framework for information retrieval
    Ameet Deshpande, and Mitesh M Khapra
    arXiv preprint arXiv:2010.00722, 2020
  3. SARL.png
    Sentiment Analysis for Reinforcement Learning
    Ameet Deshpande, and Eve Fleisig
    arXiv preprint arXiv:2010.02316, 2020
  4. CLEVR Parser: A Graph Parser Library for Geometric Learning on Language Grounded Image Scenes
    Raeid Saqur, and Ameet Deshpande
    In Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS), 2020


  1. Figurenet.png
    Figurenet: A deep learning model for question-answering on scientific plots
    Revanth Reddy, Rahul Ramesh, Ameet Deshpande, and Mitesh M Khapra
    In 2019 International Joint Conference on Neural Networks (IJCNN), 2019
  2. Leveraging Ontological Knowledge for Neural Language Models
    Ameet Deshpande, and Monisha Jegadeesan
    In Proceedings of the ACM India Joint International Conference on Data Science and Management of Data, 2019


  1. Hindsight.png
    Improvements on hindsight learning
    Ameet Deshpande, Srikanth Sarma, Ashutosh Jha, and Balaraman Ravindran
    arXiv preprint arXiv:1809.06719, 2018
  2. Option.png
    Discovering hierarchies using Imitation Learning from hierarchy aware policies
    Ameet Deshpande, Harshavardhan Kamarthi, and Balaraman Ravindran
    arXiv preprint arXiv:1812.00225, 2018