no code implementations • NAACL (TrustNLP) 2022 • Brihi Joshi, Aaron Chan, Ziyi Liu, Xiang Ren
For the latter, explanation regularization (ER) aims to improve NLM generalization by pushing the machine rationales to align with human rationales.
no code implementations • 22 Feb 2024 • Anisha Agarwal, Aaron Chan, Shubham Chandel, Jinu Jang, Shaun Miller, Roshanak Zilouchian Moghaddam, Yevhen Mohylevskyy, Neel Sundaresan, Michele Tufano
The integration of Large Language Models (LLMs) into Development Environments (IDEs) has become a focal point in modern software development.
1 code implementation • 6 Nov 2023 • Sahana Ramnath, Brihi Joshi, Skyler Hallinan, Ximing Lu, Liunian Harold Li, Aaron Chan, Jack Hessel, Yejin Choi, Xiang Ren
Results on five difficult question-answering datasets StrategyQA, QuaRel, OpenBookQA, NumerSense and QASC show that not only does MaRio improve task accuracy, but it also improves the self-rationalization quality of small LMs across the aforementioned axes better than a supervised fine-tuning (SFT) baseline.
no code implementations • 7 Oct 2023 • Song Jiang, Zahra Shakeri, Aaron Chan, Maziar Sanjabi, Hamed Firooz, Yinglong Xia, Bugra Akyildiz, Yizhou Sun, Jinchao Li, Qifan Wang, Asli Celikyilmaz
Breakdown analysis further highlights RESPROMPT particularly excels in complex multi-step reasoning: for questions demanding at least five reasoning steps, RESPROMPT outperforms the best CoT based benchmarks by a remarkable average improvement of 21. 1% on LLaMA-65B and 14. 3% on LLaMA2-70B.
no code implementations • 23 May 2023 • Aaron Chan, Anant Kharkar, Roshanak Zilouchian Moghaddam, Yevhen Mohylevskyy, Alec Helyar, Eslam Kamal, Mohamed Elkamhawy, Neel Sundaresan
We recognize that the current advances in machine learning can be used to detect vulnerable code patterns on syntactically incomplete code snippets as the developer is writing the code at EditTime.
1 code implementation • 11 May 2023 • Brihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan, Zhewei Tong, Shaoliang Nie, Qifan Wang, Yejin Choi, Xiang Ren
Existing metrics like task performance of the LM generating the rationales, or similarity between generated and gold rationales are not good indicators of their human utility.
no code implementations • 19 Dec 2022 • Aaron Chan, Zhiyuan Zeng, Wyatt Lake, Brihi Joshi, Hanjie Chen, Xiang Ren
First, KNIFE finetunes a teacher LM (given task input and FTR) to predict the task output, transferring reasoning knowledge from the FTRs to the teacher's hidden states.
1 code implementation • 3 Nov 2022 • Peifeng Wang, Aaron Chan, Filip Ilievski, Muhao Chen, Xiang Ren
Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters.
no code implementations • 30 Oct 2022 • Dong-Ho Lee, Akshen Kadakia, Brihi Joshi, Aaron Chan, Ziyi Liu, Kiran Narahari, Takashi Shibuya, Ryosuke Mitani, Toshiyuki Sekiya, Jay Pujara, Xiang Ren
Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model.
no code implementations • 2 Jul 2022 • Aaron Chan, Shaoliang Nie, Liang Tan, Xiaochang Peng, Hamed Firooz, Maziar Sanjabi, Xiang Ren
Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior.
1 code implementation • 25 May 2022 • Brihi Joshi, Aaron Chan, Ziyi Liu, Shaoliang Nie, Maziar Sanjabi, Hamed Firooz, Xiang Ren
to align with human rationales (Which input tokens would humans focus on?).
1 code implementation • BigScience (ACL) 2022 • Aaron Chan, Maziar Sanjabi, Lambert Mathias, Liang Tan, Shaoliang Nie, Xiaochang Peng, Xiang Ren, Hamed Firooz
An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction.
no code implementations • 24 May 2021 • Taylor Archibald, Mason Poggemann, Aaron Chan, Tony Martinez
We demonstrate that temporal stroke information recovered by TRACE from offline data can be used for handwriting synthesis and establish the first benchmarks for a stroke trajectory recovery system trained on the IAM online handwriting dataset.
1 code implementation • NeurIPS 2021 • Aaron Chan, Jiashu Xu, Boyuan Long, Soumya Sanyal, Tanishq Gupta, Xiang Ren
and fine (Which nodes/paths in the KG are useful?)
no code implementations • 22 Dec 2020 • Aaron Chan, Erik Darpö, Osamu Iyama, René Marczinzik
We also show that the class of twisted fractionally Calabi-Yau algebras is closed under derived equivalence, answering a question by Herschend and Iyama.
Representation Theory Rings and Algebras 16G10, 16D50, 16E05, 16E65
1 code implementation • Findings (ACL) 2021 • Jun Yan, Mrigank Raman, Aaron Chan, Tianyu Zhang, Ryan Rossi, Handong Zhao, Sungchul Kim, Nedim Lipka, Xiang Ren
Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks.
1 code implementation • ICLR 2021 • Mrigank Raman, Aaron Chan, Siddhant Agarwal, Peifeng Wang, Hansen Wang, Sungchul Kim, Ryan Rossi, Handong Zhao, Nedim Lipka, Xiang Ren
Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation.
no code implementations • CVPR 2018 • Gedas Bertasius, Aaron Chan, Jianbo Shi
We present a model that uses a single first-person image to generate an egocentric basketball motion sequence in the form of a 12D camera configuration trajectory, which encodes a player's 3D location and 3D head orientation throughout the sequence.
1 code implementation • 14 Mar 2017 • Georgios Pavlakos, Xiaowei Zhou, Aaron Chan, Konstantinos G. Derpanis, Kostas Daniilidis
This paper presents a novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image.
Ranked #1 on Keypoint Detection on Pascal3D+