activity
20192026
most citedBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

565 citations · 1.2k across the 49 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

cs.CL2021★ 3 cited

Reframing Instructional Prompts to GPTk's Language

Swaroop Mishra, Daniel Khashabi, Chitta Baral +2

What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important f…

eess.SY2021

Development of User-friendly Smart Grid Architecture

Swaroop Mishra

As systems like smart grid continue to become complex on a daily basis, emerging issues demand complex solutions that can deal with parameters in multiple domains of engineering. T…

cs.CL2021

Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systems

Neeraj Varshney, Swaroop Mishra, Chitta Baral

Standard NLP tasks do not incorporate several common real-world scenarios such as seeking clarifications about the question, taking advantage of clues, abstaining in order to avoid…

cs.LG2021

Front Contribution instead of Back Propagation

Swaroop Mishra, Anjana Arunkumar

Deep Learning's outstanding track record across several domains has stemmed from the use of error backpropagation (BP). Several studies, however, have shown that it is impossible t…

cs.CL2021★ 4 cited

How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation

Swaroop Mishra, Anjana Arunkumar

Models that top leaderboards often perform unsatisfactorily when deployed in real world applications; this has necessitated rigorous and expensive pre-deployment model testing. A h…

cs.CL2021

Constructing Flow Graphs from Procedural Cybersecurity Texts

Kuntal Kumar Pal, Kazuaki Kashihara, Pratyay Banerjee +3

Following procedural texts written in natural languages is challenging. We must read the whole text to identify the relevant information or identify the instruction flows to comple…

cs.CL2021★ 5 cited

Cross-Task Generalization via Natural Language Crowdsourcing Instructions

Swaroop Mishra, Daniel Khashabi, Chitta Baral +1

Humans (e.g., crowdworkers) have a remarkable ability in solving different tasks, by simply reading textual instructions that define them and looking at a few examples. Despite the…