Search Results for author:
Found 7 papers, 6 papers with code
Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences
With availability of such quality ratings for multiple responses, we propose utilizing these responses to create multiple preference pairs for a given prompt.
Improving Selective Visual Question Answering by Learning from Your Peers
In this work, we explore Selective VQA in both in-distribution (ID) and OOD scenarios, where models are presented with mixtures of ID and OOD data.
Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers
Extensive experiments on two benchmark datasets across three state-of-the-art MWP solvers show that proposed methods increase the generalization and robustness of existing solvers.
Adversarial Examples for Evaluating Math Word Problem Solvers
Standard accuracy metrics have shown that Math Word Problem (MWP) solvers have achieved high performance on benchmark datasets.
A Strong Baseline for Query Efficient Attacks in a Black Box Setting
Also, prior attacks do not maintain a consistent search space while comparing different search methods.
Generating Natural Language Attacks in a Hard Label Black Box Setting
Our proposed attack strategy leverages population-based optimization algorithm to craft plausible and semantically similar adversarial examples by observing only the top label predicted by the target model.
A Context Aware Approach for Generating Natural Language Attacks
We study an important task of attacking natural language processing models in a black box setting.
