no code implementations • EMNLP 2021 • Ananth Balashankar, Xuezhi Wang, Ben Packer, Nithum Thain, Ed Chi, Alex Beutel
By implementing RDI in the context of toxicity detection, we find that accounting for secondary attributes can significantly improve robustness, with improvements in sliced accuracy on the original dataset up to 7% compared to existing robustness methods.
no code implementations • 18 Apr 2024 • Zhaofeng Wu, Ananth Balashankar, Yoon Kim, Jacob Eisenstein, Ahmad Beirami
In this work, we evaluate a simple approach for zero-shot cross-lingual alignment, where a reward model is trained on preference data in one source language and directly applied to other target languages.
no code implementations • 25 Oct 2023 • Ananth Balashankar, Xiao Ma, Aradhana Sinha, Ahmad Beirami, Yao Qin, Jilin Chen, Alex Beutel
As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well.
no code implementations • 25 Oct 2023 • Aradhana Sinha, Ananth Balashankar, Ahmad Beirami, Thi Avrahami, Jilin Chen, Alex Beutel
We demonstrate the advantages of this system on the ANLI and hate speech detection benchmark datasets - both collected via an iterative, adversarial human-and-model-in-the-loop procedure.
no code implementations • 22 May 2023 • Ananth Balashankar, Xuezhi Wang, Yao Qin, Ben Packer, Nithum Thain, Jilin Chen, Ed H. Chi, Alex Beutel
We demonstrate that with a small amount of human-annotated counterfactual data (10%), we can generate a counterfactual augmentation dataset with learned labels, that provides an 18-20% improvement in robustness and a 14-21% reduction in errors on 6 out-of-domain datasets, comparable to that of a fully human-annotated counterfactual dataset for both sentiment classification and question paraphrase tasks.
no code implementations • 17 Nov 2021 • Ananth Balashankar, Lakshminarayanan Subramanian, Samuel P. Fraiberger
Anticipating the outbreak of a food crisis is crucial to efficiently allocate emergency relief and reduce human suffering.
no code implementations • ACL 2021 • Ananth Balashankar, Lakshminarayanan Subramanian
By incorporating these faithfulness properties, we learn text embeddings that are 31. 3{\%} more faithful to human validated causal graphs with about 800K and 200K causal links and achieve 21. 1{\%} better Precision-Recall AUC in a link prediction fine-tuning task.
no code implementations • 1 Oct 2020 • Yan Shvartzshnaider, Ananth Balashankar, Vikas Patidar, Thomas Wies, Lakshminarayanan Subramanian
This paper formulates a new task of extracting privacy parameters from a privacy policy, through the lens of Contextual Integrity, an established social theory framework for reasoning about privacy norms.
no code implementations • IJCNLP 2019 • Ananth Balashankar, Sun Chakraborty, an, Samuel Fraiberger, Lakshminarayanan Subramanian
We propose a new framework to uncover the relationship between news events and real world phenomena.
no code implementations • 30 Oct 2019 • Ananth Balashankar, Alyssa Lees, Chris Welty, Lakshminarayanan Subramanian
The potential for learned models to amplify existing societal biases has been broadly recognized.
no code implementations • 24 Oct 2019 • Ananth Balashankar, Alyssa Lees
We demonstrate that for a classifier to approach a definition of fairness in terms of specific sensitive variables, adequate subgroup population samples need to exist and the model dimensionality has to be aligned with subgroup population distributions.
no code implementations • WS 2018 • Yan Shvartzshanider, Ananth Balashankar, Thomas Wies, Lakshminarayanan Subramanian
We describe our experiences in using an open domain question answering model (Chen et al., 2017) to evaluate an out-of-domain QA task of assisting in analyzing privacy policies of companies.
no code implementations • WS 2018 • Ananth Balashankar, Sun Chakraborty, an, Lakshminarayanan Subramanian
We present Word Influencer Networks (WIN), a graph framework to extract longitudinal temporal relationships between any pair of informative words from news streams.
Relationship Extraction (Distant Supervised) Stock Price Prediction