no code implementations • Findings (EMNLP) 2021 • Faeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao, Mrinmaya Sachan, Snigdha Chaturvedi
When reading a literary piece, readers often make inferences about various characters’ roles, personalities, relationships, intents, actions, etc.
no code implementations • 20 Mar 2024 • JaeHun Jung, Ximing Lu, Liwei Jiang, Faeze Brahman, Peter West, Pang Wei Koh, Yejin Choi
The current winning recipe for automatic summarization is using proprietary large-scale language models (LLMs) such as ChatGPT as is, or imitation learning from them as teacher models.
1 code implementation • 16 Nov 2023 • Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Raja Marjieh, Nanyun Peng, Yejin Choi, Thomas L. Griffiths, Faeze Brahman
We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting.
no code implementations • 16 Nov 2023 • Yash Kumar Lal, Li Zhang, Faeze Brahman, Bodhisattwa Prasad Majumder, Peter Clark, Niket Tandon
Our approach is to test several simple multi-LLM-agent architectures for customization, as well as an end-to-end LLM, using a new evaluation set, called CustomPlans, of over 200 WikiHow procedures each with a customization need.
no code implementations • 14 Nov 2023 • Wenting Zhao, Justin T Chiu, Jena D. Hwang, Faeze Brahman, Jack Hessel, Sanjiban Choudhury, Yejin Choi, Xiang Lorraine Li, Alane Suhr
To instead investigate the ability to model unusual, unexpected, and unlikely situations, we explore the task of uncommonsense abductive reasoning.
1 code implementation • 13 Nov 2023 • Skyler Hallinan, Faeze Brahman, Ximing Lu, JaeHun Jung, Sean Welleck, Yejin Choi
We propose STEER: Unified Style Transfer with Expert Reinforcement, a unified frame-work developed to overcome the challenge of limited parallel data for style transfer.
1 code implementation • 13 Nov 2023 • Huihan Li, Yuting Ning, Zeyi Liao, Siyuan Wang, Xiang Lorraine Li, Ximing Lu, Wenting Zhao, Faeze Brahman, Yejin Choi, Xiang Ren
We further use the data generated by LINK to construct a dataset Logic-Induced-Long-Tail (LINT) that can be used to evaluate downstream models on the long-tail distribution; LINT contains 108K knowledge statements spanning four domains.
1 code implementation • 9 Nov 2023 • Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin
To foster generalizable agent learning, we collect large-scale, unified, and high-quality training annotations derived from diverse ground-truth reasoning rationales across various complex interactive tasks.
no code implementations • 31 Oct 2023 • 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
Specifically, we propose and test the Generative AI Paradox hypothesis: generative models, having been trained directly to reproduce expert-like outputs, acquire generative capabilities that are not contingent upon -- and can therefore exceed -- their ability to understand those same types of outputs.
no code implementations • 24 Oct 2023 • Kavel Rao, Liwei Jiang, Valentina Pyatkin, Yuling Gu, Niket Tandon, Nouha Dziri, Faeze Brahman, Yejin Choi
From this model we distill a high-quality dataset, \delta-Rules-of-Thumb, of 1. 2M entries of contextualizations and rationales for 115K defeasible moral actions rated highly by human annotators 85. 9% to 99. 8% of the time.
1 code implementation • 23 Oct 2023 • Tenghao Huang, Ehsan Qasemi, Bangzheng Li, He Wang, Faeze Brahman, Muhao Chen, Snigdha Chaturvedi
Storytelling's captivating potential makes it a fascinating research area, with implications for entertainment, education, therapy, and cognitive studies.
no code implementations • 22 Sep 2023 • Tuhin Chakrabarty, Vishakh Padmakumar, Faeze Brahman, Smaranda Muresan
The development of large language models (LLMs) capable of following instructions and engaging in conversational interactions sparked increased interest in their utilization across various support tools.
1 code implementation • 31 May 2023 • Faeze Brahman, Chandra Bhagavatula, Valentina Pyatkin, Jena D. Hwang, Xiang Lorraine Li, Hirona J. Arai, Soumya Sanyal, Keisuke Sakaguchi, Xiang Ren, Yejin Choi
In addition, we introduce a novel task, Counterfactual Planning, that requires a revision of a plan to cope with a counterfactual situation.
no code implementations • NeurIPS 2023 • Bill Yuchen Lin, Yicheng Fu, Karina Yang, Faeze Brahman, Shiyu Huang, Chandra Bhagavatula, Prithviraj Ammanabrolu, Yejin Choi, Xiang Ren
The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding.
no code implementations • 26 May 2023 • JaeHun Jung, Peter West, Liwei Jiang, Faeze Brahman, Ximing Lu, Jillian Fisher, Taylor Sorensen, Yejin Choi
We present Impossible Distillation, a novel framework for paraphrasing and sentence summarization, that distills a high-quality dataset and model from a low-quality teacher that itself cannot perform these tasks.
1 code implementation • 24 May 2023 • 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
While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure prompting can often be limited.
1 code implementation • 24 May 2023 • Ashutosh Baheti, Ximing Lu, Faeze Brahman, Ronan Le Bras, Maarten Sap, Mark Riedl
However, RLHF is an unstable and data-hungry process that continually requires new high-quality LM-generated data for finetuning.
no code implementations • 4 Dec 2022 • Faeze Brahman, Baolin Peng, Michel Galley, Sudha Rao, Bill Dolan, Snigdha Chaturvedi, Jianfeng Gao
We propose a new grounded keys-to-text generation task: the task is to generate a factual description about an entity given a set of guiding keys, and grounding passages.
1 code implementation • 2 Dec 2022 • Chao Zhao, Faeze Brahman, Kaiqiang Song, Wenlin Yao, Dian Yu, Snigdha Chaturvedi
To encourage research in this direction, we propose NarraSum, a large-scale narrative summarization dataset.
no code implementations • 1 Nov 2022 • Anvesh Rao Vijjini, Faeze Brahman, Snigdha Chaturvedi
In this paper, we introduce the task of modeling interpersonal relationships for story generation.
no code implementations • 31 Oct 2022 • Sean Welleck, Ximing Lu, Peter West, Faeze Brahman, Tianxiao Shen, Daniel Khashabi, Yejin Choi
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content.
1 code implementation • 10 Oct 2022 • Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, Swabha Swayamdipta
More concretely, we propose a metric called REV (Rationale Evaluation with conditional V-information), to quantify the amount of new, label-relevant information in a rationale beyond the information already available in the input or the label.
1 code implementation • Findings (NAACL) 2022 • Chao Zhao, Faeze Brahman, Tenghao Huang, Snigdha Chaturvedi
In particular, we hypothesize that the order of the input concepts can affect the PTM's ability to utilize its commonsense knowledge.
no code implementations • 24 May 2022 • JaeHun Jung, Lianhui Qin, Sean Welleck, Faeze Brahman, Chandra Bhagavatula, Ronan Le Bras, Yejin Choi
Despite their impressive capabilities, large pre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide the inference has emerged as a promising direction to amend this.
1 code implementation • Findings (EMNLP) 2021 • Tenghao Huang, Faeze Brahman, Vered Shwartz, Snigdha Chaturvedi
Pre-trained language models learn socially harmful biases from their training corpora, and may repeat these biases when used for generation.
no code implementations • 12 Sep 2021 • Faeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao, Mrinmaya Sachan, Snigdha Chaturvedi
When reading a literary piece, readers often make inferences about various characters' roles, personalities, relationships, intents, actions, etc.
1 code implementation • EMNLP 2021 • Somnath Basu Roy Chowdhury, Faeze Brahman, Snigdha Chaturvedi
We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets.
no code implementations • 14 Dec 2020 • Faeze Brahman, Vered Shwartz, Rachel Rudinger, Yejin Choi
In this paper, we investigate the extent to which neural models can reason about natural language rationales that explain model predictions, relying only on distant supervision with no additional annotation cost for human-written rationales.
1 code implementation • 11 Dec 2020 • Daniel Khashabi, Arman Cohan, Siamak Shakeri, Pedram Hosseini, Pouya Pezeshkpour, Malihe Alikhani, Moin Aminnaseri, Marzieh Bitaab, Faeze Brahman, Sarik Ghazarian, Mozhdeh Gheini, Arman Kabiri, Rabeeh Karimi Mahabadi, Omid Memarrast, Ahmadreza Mosallanezhad, Erfan Noury, Shahab Raji, Mohammad Sadegh Rasooli, Sepideh Sadeghi, Erfan Sadeqi Azer, Niloofar Safi Samghabadi, Mahsa Shafaei, Saber Sheybani, Ali Tazarv, Yadollah Yaghoobzadeh
Despite the progress made in recent years in addressing natural language understanding (NLU) challenges, the majority of this progress remains to be concentrated on resource-rich languages like English.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Faeze Brahman, Alexandru Petrusca, Snigdha Chaturvedi
Previous approaches in this domain have focused largely on one-shot generation, where a language model outputs a complete story based on limited initial input from a user.
1 code implementation • EMNLP 2020 • Faeze Brahman, Snigdha Chaturvedi
Emotions and their evolution play a central role in creating a captivating story.