Search Results for author: Aaron Chan

Found 19 papers, 9 papers with code

ER-TEST Evaluating Explanation Regularization Methods for NLP Models

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.

Tailoring Self-Rationalizers with Multi-Reward Distillation

1 code implementation6 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.

Question Answering StrategyQA

Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models

no code implementations7 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.


Transformer-based Vulnerability Detection in Code at EditTime: Zero-shot, Few-shot, or Fine-tuning?

no code implementations23 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.

Vulnerability Detection

Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales

1 code implementation11 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.

KNIFE: Distilling Reasoning Knowledge From Free-Text Rationales

no code implementations19 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.

Knowledge Distillation Language Modelling +1

PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales

1 code implementation3 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.

counterfactual Decision Making

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

no code implementations30 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.

text-classification Text Classification

FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales

no code implementations2 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.

Hallucination Language Modelling +2

UNIREX: A Unified Learning Framework for Language Model Rationale Extraction

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.

Language Modelling text-classification +1

TRACE: A Differentiable Approach to Line-level Stroke Recovery for Offline Handwritten Text

no code implementations24 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.

Dynamic Time Warping Handwriting Recognition

Periodic trivial extension algebras and fractionally Calabi-Yau algebras

no code implementations22 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

Egocentric Basketball Motion Planning from a Single First-Person Image

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.

Motion Planning

6-DoF Object Pose from Semantic Keypoints

1 code implementation14 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.

Keypoint Detection Object +1

Cannot find the paper you are looking for? You can Submit a new open access paper.