activity
20152022
most citedHow Much Can CLIP Benefit Vision-and-Language Tasks?

153 citations · 601 across the 67 of their papers we have counts for

collaborators
Showing cs.CLShow all

95 papers · 1 filter

cs.CL2022

Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality

Yichen Jiang, Xiang Zhou, Mohit Bansal

Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. In this work, we analyze this behavior of seq2seq models and ident…

cs.CL20221 cited

Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations

Swarnadeep Saha, Peter Hase, Nazneen Rajani +1

Recent work on explainable NLP has shown that few-shot prompting can enable large pretrained language models (LLMs) to generate grammatical and factual natural language explanation…

cs.CL2022

Evaluating and Improving Factuality in Multimodal Abstractive Summarization

David Wan, Mohit Bansal

Current metrics for evaluating factuality for abstractive document summarization have achieved high correlations with human judgment, but they do not account for the vision modalit…

cs.CL2022

On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets

Hyounghun Kim, Aishwarya Padmakumar, Di Jin +2

Natural language guided embodied task completion is a challenging problem since it requires understanding natural language instructions, aligning them with egocentric visual observ…

cs.CL20221 cited

FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization

David Wan, Mohit Bansal

We present FactPEGASUS, an abstractive summarization model that addresses the problem of factuality during pre-training and fine-tuning: (1) We augment the sentence selection strat…

cs.CL20221 cited

Efficient Few-Shot Fine-Tuning for Opinion Summarization

Arthur Bražinskas, Ramesh Nallapati, Mohit Bansal +1

Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. However, in opi…