Karthikeyan Natesan Ramamurthy

Karthikeyan Natesan Ramamurthy

Auto-generated profile, based on publicly available information

Karthikeyan Natesan Ramamurthy

IBM Research IBM Research IBM Research IBM Research IBM Research

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2019 in IBM Journal of Research and Development
Verified
Journal Article
Closed access
RBR. K. E. Bellamy
R. K. E. Bellamy
KDK. Dey
K. Dey
MHM. Hind
M. Hind
SHS. C. Hoffman
S. C. Hoffman
SHS. Houde
S. Houde
YZY. Zhang
Y. Zhang

1 July 2019 in IBM Journal of Research and Development
Verified
Journal Article
Closed access
MAM. Arnold
M. Arnold
RBR. K. E. Bellamy
R. K. E. Bellamy
MHM. Hind
M. Hind
SHS. Houde
S. Houde
SMS. Mehta
S. Mehta
KVKush Varshney
Kush Varshney

19 March 2023
Verified
Conference Paper
Open access
TDTim Draws
Tim Draws
KRKarthikeyan Natesan Ramamurthy
Karthikeyan Natesan Ramamurthy
IBIoana Baldini
Ioana Baldini
ADAmit Dhurandhar
Amit Dhurandhar
IPInkit Padhi
Inkit Padhi
NTNava Tintarev
Nava Tintarev
One way to help users navigate debated topics online is to apply stance detection in web search. Automatically identifying whether search results are against, neutral, or in favor could facilitate diversification efforts and support interventions that aim to mitigate cognitive biases. To be truly useful in this context, however, stance detection models not only need to make accurate (cross-topic) predictions but also be sufficiently explainable to users when applied to search results – an issue that is currently unclear. This paper presents a study into the feasibility of using current stance detection approaches to assist users in their web search on debated topics. We train and evaluate 10 stance detection models using a stance-annotated data set of 1204 search results. In a preregistered user study (N = 291), we then investigate the quality of stance detection explanations created using different explainability methods and explanation visualization techniques. The models we implement predict stances of search results across topics with satisfying quality (i.e., similar to the state-of-the-art for other data types). However, our results reveal stark differences in explanation quality (i.e., as measured by users’ ability to simulate model predictions and their attitudes towards the explanations) between different models and explainability methods. A qualitative analysis of textual user feedback further reveals potential application areas, user concerns, and improvement suggestions for such explanations. Our findings have important implications for the development of user-centered solutions surrounding web search on debated topics.

1 November 2017 in IBM Journal of Research and Development
Verified
Journal Article
Closed access
CKC. Kuhlman
C. Kuhlman
KRK. N. Ramamurthy
K. N. Ramamurthy
Prasanna SattigeriPrasanna Sattigeri
Prasanna Sattigeri
ALA. C. Lozano
A. C. Lozano
LCL. Cao
L. Cao
KVKush Varshney
Kush Varshney
Innovation is a key factor driving economic growth in countries worldwide. However, innovation is hard to define and, therefore, even harder to measure. To help policy makers and business leaders better understand how to foster innovation, we need robust ways to quantify innovation at local and global scales. In this work, we use a data-driven, machine-learning approach for measuring innovation. Analyzing a large number of country-level metrics, we aim to automatically discover actionable “levers” of innovation. Using unsupervised learning methods, we determine groups of related world development indicators among a collection compiled by the World Bank. We then train a Group Lasso predictive model using data from the World Economic Forum (WEF) that captures the perceived level of innovation in 150 countries. Aside from providing high predictive accuracy, the Group Lasso also provides a model that is easily interpretable. The result is the Open Innovation Index (OII), an automatic global model for measuring innovation using machine learning algorithms and open data. We predict the OII scores for countries that only have World Development Indicators data and no existing WEF innovation scores. Furthermore, we also present case studies for which the innovation levers of a few representative countries are uncovered automatically by the proposed model.

6 October 2018
Verified
Book Chapter
Closed access
PDF file
ASAnirudh Som
Anirudh Som
KTKowshik Thopalli
Kowshik Thopalli
KRKarthikeyan Natesan Ramamurthy
Karthikeyan Natesan Ramamurthy
VVVinay Venkataraman
Vinay Venkataraman
ASAnkita Shukla
Ankita Shukla
PTPavan Turaga
Pavan Turaga

5 September 2024 in IEEE Internet Computing
Verified
Journal Article
Closed access
SASwapnaja Achintalwar
Swapnaja Achintalwar
IBIoana Baldini
Ioana Baldini
DBDjallel Bouneffouf
Djallel Bouneffouf
JBJoan Byamugisha
Joan Byamugisha
MCMaria Chang
Maria Chang
KVKush Varshney
Kush Varshney
The alignment of large language models is usually done by model providers to add or control behaviors that are common or universally understood across use cases and contexts. In contrast, in this article, we present an approach and architecture that empowers application developers to tune a model to their particular values, social norms, laws and other regulations, and orchestrate between potentially conflicting requirements in context. We lay out three main components of such an Alignment Studio architecture: Framers, Instructors, and Auditors that work in concert to control the behavior of a language model. We illustrate this approach with a running example of aligning a company’s internal-facing enterprise chatbot to its business conduct guidelines.