/ɑ.bʰi.ˈla.ʃə/ (listen)
Abhilasha Ravichander👋
I am a Postdoc/Young Investigator at the Allen Institute for AI (AI2), working on project Mosaic. Prior to joining AI2, I completed my PhD from Carnegie Mellon University. My research focuses on building robust systems to process natural language, by: (1) formulating techniques to diagnose and validate models and datasets, (2) developing stronger computational reasoning capabilities, and (3) explaining the predictive decision-making mechanisms of models. Ultimately, I care about making trustworthy technology that people can use. To this end, I am also interested in building tools that empower people to take (back) control of their privacy. For more about my work, please see my publications.
What's New
Artifacts or Abduction? was presented at MASC-SLL 2024 and won a best paper
award 🎉
I am co-organizing the Workshop on Privacy in Natural Language Processing @ACL 2024
I co-organized the Workshop on Representation Learning for NLP @ ACL 2023.
Talk at the National University of Singapore.
Talk at UMass NLP.
I will be at the Rising Stars in EECS workshop
at the University of Texas at Austin.
CondaQA won a best paper
award at the 2022 SoCal NLP
symposium 🎉
I was selected as a Rising Star in Data
Science by the University of Chicago.
I was an outstanding reviewer at ACL 2020 and EMNLP 2020.
I started the NLP With Friends online seminar series,
with my wonderful co-organizers Zeerak Waseem, Yanai Elazar and Liz Salesky.
I will be speaking in a panel on "The Role of Active Privacy Management in a
World Where the
Consent Model Breaks Down" at CPDP 2020 in
Brussels, Belgium.
I will be helping lead a research team at the OurCS workshop at CMU. If you are an undergraduate woman,
please
do consider attending! Funds for hotels and meals will be provided.
I will be spending the summer interning at MSR Montreal with Adam Trischler
and Kaheer Suleman,
working on teaching machines commonsense reasoning.
I will be attending ACL, YRRSDS and SIGDIAL 2018 in Melbourne. Ping me if you'd like to
chat!
Our work, "Stress Test Evaluation for Natural Language Inference" was an Area Chair Favorite Paper at COLING
2018!
I will be at the Generalization in Deep
Learning workshop at NAACL 2018. Ping me if you'd like to chat!
I will be starting my PhD at the Language Technologies Institute, Carnegie
Mellon University in
Fall 2018.
I am at the Machine Learning Summer School in
Tubingen. Let me know if you'd like to meet up!
Our team was selected to participate in the Alexa
Prize with a 100,000$ stipend and additional support from Amazon! Congratulations to all the
selected teams.
Our work on "A Persistent Homology Approach to Document Clustering" won the best poster award in
10-701 (Introduction to Machine Learning (PhD)).
Publications
(*) - Equal Contribution2024
Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question? MASC-SLL 2024 best paper award
Nishant Balepur, Abhilasha Ravichander, Rachel Rudinger
arxiv
PDF Code/Data Long OLMo: Accelerating the Science of Language Models GeekWire Innovation of the Year award Dirk Groeneveld, Iz Beltagy, Pete Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Harsh Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Raghavi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew E. Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, Will Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah A. Smith, Hannaneh Hajishirzi
arxiv
PDF Code/Data Long Press: TechCrunch VentureBeat Forbes GeekWire Axios SD Times Fast Company Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research Luca Soldaini, Rodney Kinney, Akshita Bhagia, Dustin Schwenk, David Atkinson, Russell Authur, Ben Bogin, Khyathi Chandu, Jennifer Dumas, Yanai Elazar, Valentin Hofmann, Ananya Harsh Jha, Sachin Kumar, Li Lucy, Xinxi Lyu, Nathan Lambert, Ian Magnusson, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew E. Peters, Abhilasha Ravichander, Kyle Richardson, Zejiang Shen, Emma Strubell, Nishant Subramani, Oyvind Tafjord, Pete Walsh, Luke Zettlemoyer, Noah A. Smith, Hannaneh Hajishirzi, Iz Beltagy, Dirk Groeneveld, Jesse Dodge, Kyle Lo
arxiv
PDF Code/Data Long Press: TechCrunch Marktechpost Voicebot Agent Lumos: Unified and Modular Training for Open-Source Language Agents Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin
arxiv
PDF Code/Data Long Website Press: Marktechpost MacGyver: Are Large Language Models Creative Problem Solvers? Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Raja Marjieh, Nanyun Peng, Yejin Choi, Thomas L Griffiths, Faeze Brahman
2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024)
PDF Code/Data Long What’s In My Big Data? Yanai Elazar, Akshita Bhagia, Ian Magnusson, Abhilasha Ravichander, Dustin Schwenk, Alane Suhr, Evan Pete Walsh, Dirk Groeneveld, Luca Soldaini, Sameer Singh, Hannaneh Hajishirzi, Noah A. Smith, Jesse Dodge 2024 International Conference on Learning Representations, (ICLR 2024). PDF Code/Data Long Website Press: Marktechpost The Generative AI Paradox: “What It Can Create, It May Not Understand” Peter West, Ximing Lu, Nouha Dziri, Faeze Brahman, Linjie Li, Jena D. Hwang, Liwei Jiang, Jillian Fisher, Abhilasha Ravichander, Khyathi Chandu, Benjamin Newman, Pang Wei Koh, Allyson Ettinger, Yejin Choi 2024 International Conference on Learning Representations, (ICLR 2024).
PDF Long The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, Yejin Choi 2024 International Conference on Learning Representations, (ICLR 2024).
PDF Code/Data Long Website Understanding How to Inform Blind and Low-Vision Users about Data Privacy through Privacy Question Answering Assistants Yuanyuan Feng, Abhilasha Ravichander, Yaxing Yao, Shikun Zhang, Rex Chen, Shomir Wilson, Norman Sadeh USENIX Security 2024. PDF Long