Pradeep Dasigi

I am a research scientist on the AllenNLP team at the Allen Institute for AI. I have been actively involved in developing open language models, OLMo and Tulu. I currently work on post-training language models, and am generally passionate about adapting language models for general use with minimal human effort.

Research Themes

Check out the full list of my papers for an up-to-date overview of my research. The following are the core themes of my work and some associated selected publications.

• Open Language Modeling Recipes
  • Tulu 3: Pushing Frotiers in Open Language Model Post-Training
  • How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
• Efficient Adaptation of Language Models
  • Large-Scale Data Selection for Instruction Tuning
  • Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
  • Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
  • Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
  • Data-Efficient Finetuning Using Cross-Task Nearest Neighbors
• Robustness to Distribution Shifts
  • TRAM: Bridging Trust Regions and Sharpness Aware Minimization
  • AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization
  • Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets
• Evaluation Benchmarks and Guidelines
• LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
• A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
• Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
• DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

Mentorship

I have been fortunate to work with many talented interns and pre-doctoral researchers over the years.

Pre-doctoral researchers

• Jacob Morrison → PhD student, University of Washington
• Lj Miranda → PhD student, University of Cambridge
• Xinxi Lyu → PhD student, University of Illinois Urbana-Champaign

Interns

• Shakti Senthil, Senior, University of Washington (2025)
• Clara Na, PhD student, Carnegie Mellon University (2023)
• Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
• Arkil Patel, Masters student, McGill University (2023)
• Evaluating In-Context Learning of Libraries for Code Generation
• Tom Sherborne, PhD student, University of Edinburgh (2023)
• TRAM: Bridging Trust Regions and Sharpness Aware Minimization
• Kalpesh Krishna, PhD student, University of Massachusetts, Amherst (2022)
• LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
• Revanth Gangi Reddy, PhD student, University of Illinois University of Illinois Urbana-Champaign (2022)
• A Large-Scale Study of Reranker Relevance Feedback at Inference
• Bhargavi Paranjape, PhD student, University of Washington (2022)
• AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization
• Vidhisha Balachandran, PhD student, Carnegie Mellon University (2021)
• Yuxiang Wu, PhD student, University College London (2021)
• Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets
• Ansong Ni, Masters student, Carnegie Mellon University (2020)
• Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization
• James Ferguson, PhD student, University of Washington (2020)
• IIRC: A Dataset of Incomplete Information Reading Comprehension Questions
• Zhanming Allan Jie, PhD student, Singapore University of Technology and Design (2019)

Podcast

I used to be a frequent host on the NLP Highlights podcast along with other members of the AllenNLP team.