activity
20122026
most citedFooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods

168 citations · 646 across the 40 of their papers we have counts for

collaborators
Showing 2021 · cs.CLShow all

8 papers · 2 filters

cs.CL2021

Enforcing Consistency in Weakly Supervised Semantic Parsing

Nitish Gupta, Sameer Singh, Matt Gardner

The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate searc…

cs.CL20215 cited

Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models

Robert L. Logan, Ivana Balažević, Eric Wallace +3

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuni…

cs.CL20211 cited

Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP

Anthony Chen, Pallavi Gudipati, Shayne Longpre +2

Retrieval is a core component for open-domain NLP tasks. In open-domain tasks, multiple entities can share a name, making disambiguation an inherent yet under-explored problem. We…

cs.CL2021

Generative Context Pair Selection for Multi-hop Question Answering

Dheeru Dua, Cicero Nogueira dos Santos, Patrick Ng +4

Compositional reasoning tasks like multi-hop question answering, require making latent decisions to get the final answer, given a question. However, crowdsourced datasets often cap…

cs.CL2021

Learning with Instance Bundles for Reading Comprehension

Dheeru Dua, Pradeep Dasigi, Sameer Singh +1

When training most modern reading comprehension models, all the questions associated with a context are treated as being independent from each other. However, closely related quest…

cs.CL20211 cited

An Empirical Comparison of Instance Attribution Methods for NLP

Pouya Pezeshkpour, Sarthak Jain, Byron C. Wallace +1

Widespread adoption of deep models has motivated a pressing need for approaches to interpret network outputs and to facilitate model debugging. Instance attribution methods constit…