Hi there! I’m Abhinav, a senior at UIUC majoring in Computer Science. My research focuses on preference learning and reasoning in large language models. I am fortunate to be advised by Prof. Dilek Hakkani-Tür and Prof. Heng Ji.

Currently, I am exploring scientific reasoning in LLMs at ConvAI Lab and working as a research intern at Sandia National Labs.

Feel free to reach out to me at achinta3[at]illinois[dot]edu.

Selected Publications

* indicates equal contribution

  • Unsupervised Human Preference Learning
    [Paper][Slides][Poster]
    Sumuk Shashidhar, Abhinav Chinta, Vaibhav Sahai, and Dilek Hakkani-Tür.
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024, United States. Association for Computational Linguistics.

  • Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models
    [Paper][Slides]
    Sumuk Shashidhar*, Abhinav Chinta*, Vaibhav Sahai*, Zhenhailong Wang, and Heng Ji.
    In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9070–9084, Singapore. Association for Computational Linguistics.

  • Scaling Laws For Natural Language Planning Models.
    Abhinav Chinta, Sumuk Shashidhar, Vaibhav Sahai, Yangyi Chen, Heng Ji. Under Review.

  • Token Efficient Deep Conversational Reasoning With ConvoDAGs
    Sumuk Shashidhar*, Abhinav Chinta*, Vaibhav Sahai, Faraz Siddiqui, Shivansh Patel, Kevin Chen-Chuan Chang. Under Review.

Experience

  • Sandia National Laboratories, 05/2024 - Present
    • Position: Research Intern
    • Focus: Retrieval Augmented Generation, Large Corpus Analysis
  • ConvAI Lab, 08/2023 - Present
    • Position: Research Assistant
    • Focus: Scientific Reasoning in LLMs
  • BLENDER Lab, 06/2023 - Present
    • Position: Research Assistant
    • Focus: Domain Agnostic Self-Refinement in LLMs
  • Nference Inc., 05/2023 - 08/2023
    • Position: Machine Learning Intern
    • Focus: Tumor Detection using Deep Learning
  • Jane Street, 05/2023
    • Position: SEE Trading Fellow
    • Focus: Trading Algorithms

Education

Talks

  • Generative Agents: Interactive Simulacra of Human Behavior [Slides]
  • Self-Refine: Iterative Refinement with Self-Feedback [Slides]

CV

Please find my CV here.