Faeze Brahman.

I am a post-doctoral researcher at Allen Institute for AI and the Paul G. Allen School of Computer Science & Engineering at the University of Washington working with Prof. Yejin Choi. Prior to this, I did my Ph.D. (2022) in Computer Science at the University of California, Santa Cruz, working with Prof. Snigdha Chaturvedi. I hold a master degree (2018) in Computer Science and a master (2014) and bachelor (2012) degree in Electrical Engineering.

 

I am broadly interested in natural language understanding and generation with the long-term goal of instilling human-like communication, commonsense knowledge, and reasoning capabilities in machines. My current research interests include (controllable) text generation, (social) commonsense reasoning, and unsupervised learning.


Previously, I interned at Microsoft Research, working on controllable grounded text generation; and at AI2, working on unsupervised rationale generation for non-monotonic reasoning.



News

May 2022: REV accepted to ACL 2023!

March 2023: Talk at UMass NLP Seminars!

Jan 2023: We'll be back with 5th iteration of Narrative Understanding Workshopi, this time at ACL 2023!

Jan 2023: Self-correct paper accepted at ICLR 2023!

Oct 2022: 4 papers accepted to EMNLP 2022 (2 main, 2 findings). Stay tuned !

Oct 2022: New preprint with my intern on Information-theoretic Evaluation of Free-Text Rationales !

July 2022: Co-organized the 4th successful workshop on Narrative Understanding at NAACL 2021 (Seattle)!

May 2022: New preprint on maieutic prompting for logically consistent reasoning!

April 2022: Joined AI2 as a young investigator working with Yejin Choi!

Jan 2022: Talk at The University of British Columbia!

Jan 2022: Talk at The University of Southern California!

Nov 2021: Co-organizing the 4th edition of Narrative Understanding workshop to be collocated with NAACL 2022.

Sept 2021: I've been awarded the Jack Baskin School of Engineering 2021 Sabbatical Fellowship!

June 2021: I will be interning with Michel Galley and Jianfeng Gao at Microsoft Research (MSR) in Redmond!

Nov 2020: Our paper Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision has been accepted to AAAI 2021! Work done during my internship @ AI2!

Nov 2020: I am co-organizing a workshop with Snigdha Chaturvedi, Mohit Iyyer, Elizabeth Clark, Lara J. Martin, and Nader Akoury on Narrative Understanding @ NAACL 2021.

Sept 2020: Our long paper on Modeling Protagonist Emotions for Emotion-Aware Storytelling has been accepted to EMNLP 2020!

Sept 2020: I successfully advanced to candidacy. Officially a Ph.D. candidate now!

June 2020: Excited to join the MOSAIC team at Allen Institute of AI as a research intern this summer. Looking forward to new collaborations.

Publications

You can also find my papers on my Semantic Scholar Profile or my Google Scholar profile.


Preprints

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
Ximing Lu, Faeze Brahman, Peter West, Jaehun Jang, Khyathi Chandu, Abhilasha Ravichander, Lianhui Qin, Prithviraj Ammanabrolu, Liwei Jiang, Sahana Ramnath, Nouha Dziri, Jillian Fisher, Bill Yuchen Lin, Skyler Hallinan, Xiang Ren, Sean Welleck, Yejin Choi
[preprint]


Improving Language Models with Advantage-based Offline Policy Gradients
Ashutosh Baheti, Ximing Lu, Faeze Brahman, Ronan Le Bras, Maarten Sap, Mark Riedl
[preprint]


2023

REV: Information-Theoretic Evaluation of Free-Text Rationales
Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, Swabha Swayamdipta
In Proceedings of ACL 2023.
[preprint]


Generating Sequences by Learning to [Self-]Correct
Sean Welleck*, Ximing Lu*, Peter West+, Faeze Brahman+, Tianxiao Shen, Daniel Khashabi, Yejin Choi
Accepted to appear at ICLR 2023
(* co-first authors, + co-second authors)
[preprint]


2022

Information-Theoretic Evaluation of Free-Text Rationales with Conditional V-Information
Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, Swabha Swayamdipta
Trustworthy and Socially Responsible Machine Learning (TSRML) Workshop @ NeurIPS 2022.
[paper]


Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
Jaehun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, Yejin Choi
In Proceedings of EMNLP 2022.
[paper] [code]


Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation
Faeze Brahman, Baolin Peng, Michel Galley, Sudha Rao, Bill Dolan, Snigdha Chaturvedi, Jianfeng Gao
In Findings of EMNLP 2022.
[paper] [Data & Code]


Towards Inter-character Relationship-driven Story Generation
Anvesh Rao Vijjini, Faeze Brahman, Snigdha Chaturvedi
In Proceedings of EMNLP 2022.
[paper]


NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization
Chao Zhao, Faeze Brahman, Kaiqiang Song, Wenlin Yao, Dian Yu, Snigdha Chaturvedi
In Findings of EMNLP 2022.
[paper] [data]


Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach
Chao Zhao, Faeze Brahman, Tenghao Huang, Snigdha Chaturvedi
In Findings of NAACL 2022.
[paper]


Modeling Key Narrative Elements for Story Understanding and Generation
Faeze Brahman
PhD Thesis, University of California Santa Cruz
[Abstract]


2021

"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
Faeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao, Mrinmaya Sachan, Snigdha Chaturvedi
In Findings of EMNLP 2021.
[paper] [data]


Is Everything in Order? A Simple Way to Order Sentences
Somnath Basu Roy Chowdhury*, Faeze Brahman*, Snigdha Chaturvedi
In Proceedings of EMNLP 2021.
(*equal contribution)
[paper] [code] [poster]


Uncovering Implicit Gender Bias in Narratives through Commonsense Inference
Tenghao Huang, Faeze Brahman, Vered Shwartz, Snigdha Chaturvedi
In Findings of EMNLP 2021.
[paper]


Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
Faeze Brahman, Vered Shwartz, Rachel Rudinger and Yejin Choi
In Proceedings of AAAI 2021.
[paper] [code] [slides]


PARSINLU: A Suite of Language Understanding Challenges for Persian
Daniel Khashabi et al.
In Transaction of TACL 2021.
[paper] [data & code]


2020

Modeling Protagonist Emotions for Emotion-Aware Storytelling
Faeze Brahman, Snigdha Chaturvedi
In Proceedings of EMNLP 2020.
[paper] [code] [slides] [video]


Cue Me In: Content-Inducing Approaches to Interactive Story Generation
Faeze Brahman, Alenxandru Petrusca and Snigdha Chaturvedi
In Proceedings of AACL 2020.
[paper] [slides]


Towards Emotion-Aware Storytelling Using Reinforcement Learning
Faeze Brahman, Snigdha Chaturvedi
NeurIPS 2020 Workshop, Wordplay: When Language Meets Games


Effective Forum Curation via Multi-task Learning
Faeze Brahman, Nikhil Varghese, Suma Bhat and Snigdha Chaturvedi
In Proceedings of EDM 2020.
[paper]


2019

Automatic Story Generation with Human-in-the-Loop
Faeze Brahman, Alexandru Petrusca, and Snigdha Chaturvedi
NAACL-HLT 2019 Workshop on Narrative Understanding (NUSE 2019)


2015 and before

F. Brahman, M. Honarmand, and S. Jadid. Optimal Electrical and Thermal Energy Management of a Residential Energy Hub, Integrating Demand Response and Energy Storage System, Journal of Energy and Building, Volume 90, 1 March 2015, Pages 65-75. [pdf]


S. Esmaeili, B. Vahidi, M. Parvizimosaed and F. Brahman. Development of a Thermal and Electrical Energy Management System in Residential Building Micro-Grid, Journal of Renewable and Sustainable Energy, Jan. 2013. [pdf]


F. Brahman and S. Jadid. Optimal Energy Management of Hybrid CCHP and PV in a Residential Building,"in Proceedings of EPDC 2014 [pdf]

Contact

Email: faezeb [at] allenai [dot] org

Address: 2157 N Northlake Way
Seattle, WA 98103