Search Results for author: Brihi Joshi

Found 10 papers, 7 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

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

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

The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks

1 code implementation COLING 2020 Brihi Joshi, Neil Shah, Francesco Barbieri, Leonardo Neves

Contextual embeddings derived from transformer-based neural language models have shown state-of-the-art performance for various tasks such as question answering, sentiment analysis, and textual similarity in recent years.

Question Answering Sentiment Analysis

Retweet Us, We Will Retweet You: Spotting Collusive Retweeters Involved in Blackmarket Services

1 code implementation23 Jun 2018 Hridoy Sankar Dutta, Aditya Chetan, Brihi Joshi, Tanmoy Chakraborty

Thus they become customers of blackmarket syndicates and engage in fake activities.

Social and Information Networks

Generating Clues for Gender based Occupation De-biasing in Text

1 code implementation11 Apr 2018 Nishtha Madaan, Gautam Singh, Sameep Mehta, Aditya Chetan, Brihi Joshi

Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically.

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