AIConfPaper
← Search

Karthikeyan Natesan Ramamurthy

35 accepted papers

2026

CoFrGeNet: Continued Fraction Architectures for Language Generation

Amit Dhurandhar, Vijil Chenthamarakshan, Dennis Wei, Tejaswini Pedapati, Karthikeyan Natesan Ramamurthy, Rahul Nair
ICML 2026poster

Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function class is named CoFrGeNets - Continued Fraction Generative Networ…

Cited by 0Source ↗Scholar ↗
2025

Evaluating the Prompt Steerability of Large Language Models

Erik Miehling, Michael Desmond, Karthikeyan Natesan Ramamurthy, Elizabeth M. Daly, Kush R. Varshney, Eitan Farchi +5
NAACL 2025long

Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting various personas. To this end, we propose a benchmark…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2025

Fair Continuous Resource Allocation with Equality of Impact

Blossom Metevier, Dennis Wei, Karthikeyan Natesan Ramamurthy, Philip S. Thomas
NeurIPS 2025poster

Recent works have studied fair resource allocation in social settings, where fairness is judged by the impact of allocation decisions rather than more traditional minimum or maximum thresholds on the allocations themselves. Our work significantly adds to this literature by developing continuous reso…

Cited by 0Source ↗Scholar ↗
2025

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods

Dennis Wei, Inkit Padhi, Soumya Ghosh, Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Maria Chang
NeurIPS 2025poster

Training data attribution (TDA) is concerned with understanding model behavior in terms of the training data. This paper draws attention to the common setting where one has access only to the final trained model, and not the training algorithm or intermediate information from training. We reframe th…

Cited by 0Source ↗Scholar ↗
2025

Multi-Level Explanations for Generative Language Models

Lucas Monteiro Paes, Dennis Wei, Hyo Jin Do, Hendrik Strobelt, Ronny Luss, Amit Dhurandhar +5
ACL 2025long

Despite the increasing use of large language models (LLMs) for context-grounded tasks like summarization and question-answering, understanding what makes an LLM produce a certain response is challenging. We propose Multi-Level Explanations for Generative Language Models (MExGen), a technique to prov…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Programming Refusal with Conditional Activation Steering

Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy, Erik Miehling, Pierre Dognin, Manish Nagireddy +1
ICLR 2025spotlight

LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selective responses are essential, such as content modera…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2025

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents

Ivoline C. Ngong, Swanand Ravindra Kadhe, Hao Wang, Keerthiram Murugesan, Justin D. Weisz, Amit Dhurandhar +1
ACL 2025finding

Conversational agents are increasingly woven into individuals’ personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents —such as large language models (LLMs)— their private information becomes vulnerable to exposure. I…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Sparsity May Be All You Need: Sparse Random Parameter Adaptation

Jesus Rios, Pierre Dognin, Ronny Luss, Karthikeyan Natesan Ramamurthy
EMNLP 2025

Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT) methods aim at significantly reducing the computational and memory resources needed for fine-tuning these models by only

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Position: Topological Deep Learning is the New Frontier for Relational Learning

Theodore Papamarkou, Tolga Birdal, Michael M. Bronstein, Gunnar E. Carlsson, Justin Curry, Yue Gao +16
ICML 2024poster

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporat…

Cited by 40Source ↗PDF ↗Scholar ↗
2024

Ranking Large Language Models without Ground Truth

Amit Dhurandhar, Rahul Nair, Moninder Singh, Elizabeth Daly, Karthikeyan Natesan Ramamurthy
ACL 2024findings

Evaluation and ranking of large language models (LLMs) has become an important problem with the proliferation of these models and their impact. Evaluation methods either require human responses which are expensive to acquire or use pairs of LLMs to evaluate each other which can be unreliable. In thi…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

Trust Regions for Explanations via Black-Box Probabilistic Certification

Amit Dhurandhar, Swagatam Haldar, Dennis Wei, Karthikeyan Natesan Ramamurthy
ICML 2024poster

Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Value Alignment from Unstructured Text

Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Manish Nagireddy, Pierre Dognin, Kush R. Varshney
EMNLP 2024industry

Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP. Currently, this alignment process relies on the availability of high-quality supervised and preference data, which can be both time-consuming and expensive to curate…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Cookie Consent Has Disparate Impact on Estimation Accuracy

Erik Miehling, Rahul Nair, Elizabeth M. Daly, Karthikeyan Natesan Ramamurthy, Robert Nelson Redmond
NeurIPS 2023poster

Cookies are designed to enable more accurate identification and tracking of user behavior, in turn allowing for more personalized ads and better performing ad campaigns. Given the additional information that is recorded, questions related to privacy and fairness naturally arise. How does a user's co…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models

Sourya Basu, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Vijil Chenthamarakshan, Kush R. Varshney, Lav R. Varshney +1
AAAI 2023technical

We introduce equi-tuning, a novel fine-tuning method that transforms (potentially non-equivariant) pretrained models into group equivariant models while incurring minimum L_2 loss between the feature representations of the pretrained and the equivariant models. Large pretrained models can be equi-tu…

Cited by 27Source ↗PDF ↗Scholar ↗
2023

Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning

Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Kartik Ahuja, Vijay Arya
NeurIPS 2023poster

Locally interpretable model agnostic explanations (LIME) method is one of the most popular methods used to explain black-box models at a per example level. Although many variants have been proposed, few provide a simple way to produce high fidelity explanations that are also stable and intuitive. In…

Cited by 8Source ↗PDF ↗Scholar ↗
2023

TOPO-MLP : A Simplicial Network without Message Passing

Karthikeyan Natesan Ramamurthy, Aldo Guzmán-Sáenz, Mustafa Hajij
ICASSP 2023accepted

Due to their ability to model meaningful higher order relations among a set of entities, higher order network models have emerged recently as a powerful alternative for graph-based network models which are only capable of modeling binary relationships. Message passing paradigm is still dominantly us…

Cited by 0Source ↗Scholar ↗
2022

A label efficient two-sample test

Weizhi Li, Gautam Dasarathy, Karthikeyan Natesan Ramamurthy, Visar Berisha
UAI 2022poster

Two-sample tests evaluate whether two samples are realizations of the same distribution (the null hypothesis) or two different distributions (the alternative hypothesis). We consider a new setting for this problem where sample features are easily measured whereas sample labels are unknown and costly…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2022

Augmenting Molecular Deep Generative Models with Topological Data Analysis Representations

Yair Schiff, Vijil Chenthamarakshan, Samuel C. Hoffman, Karthikeyan Natesan Ramamurthy, Payel Das
ICASSP 2022accepted

Deep generative models have emerged as a powerful tool for learning useful molecular representations and designing novel molecules with desired properties, with applications in drug discovery and material design. However, most existing deep generative models are restricted due to lack of spatial inf…

Cited by 0Source ↗Scholar ↗
2022

Is this the Right Neighborhood? Accurate and Query Efficient Model Agnostic Explanations

Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Karthikeyan Shanmugam
NeurIPS 2022accept

There have been multiple works that try to ascertain explanations for decisions of black box models on particular inputs by perturbing the input or by sampling around it, creating a neighborhood and then fitting a sparse (linear) model (e.g. LIME). Many of these methods are unstable and so more rece…

Cited by 7Source ↗PDF ↗Scholar ↗
2022

Your fairness may vary: Pretrained language model fairness in toxic text classification

Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, Moninder Singh, Mikhail Yurochkin
ACL 2022findings

The popularity of pretrained language models in natural language processing systems calls for a careful evaluation of such models in down-stream tasks, which have a higher potential for societal impact. The evaluation of such systems usually focuses on accuracy measures. Our findings in this paper c…

Cited by 72Source ↗PDF ↗Scholar ↗
2021

Conditionally independent data generation

Kartik Ahuja, Prasanna Sattigeri, Karthikeyan Shanmugam, Dennis Wei, Karthikeyan Natesan Ramamurthy, Murat Kocaoglu
UAI 2021poster

Conditional independence (CI) is a fundamental concept with wide applications in machine learning and causal inference. Although the problems of testing CI and estimating divergences have been extensively studied, the complementary problem of generating data that satisfies CI has received much less…

Cited by 5Source ↗PDF ↗Scholar ↗
2020

Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness

Pu Zhao, Pin-Yu Chen, Payel Das, Karthikeyan Natesan Ramamurthy, Xue Lin
ICLR 2020poster

Mode connectivity provides novel geometric insights on analyzing loss landscapes and enables building high-accuracy pathways between well-trained neural networks. In this work, we propose to employ mode connectivity in loss landscapes to study the adversarial robustness of deep neural networks, and…

Cited by 249Source ↗code ↗Scholar ↗
2020

Finding the Homology of Decision Boundaries with Active Learning

Weizhi Li, Gautam Dasarathy, Karthikeyan Natesan Ramamurthy, Visar Berisha
NeurIPS 2020poster

Accurately and efficiently characterizing the decision boundary of classifiers is important for problems related to model selection and meta-learning. Inspired by topological data analysis, the characterization of decision boundaries using their homology has recently emerged as a general and powerfu…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2020

Model Agnostic Multilevel Explanations

Karthikeyan Natesan Ramamurthy, Bhanukiran Vinzamuri, Yunfeng Zhang, Amit Dhurandhar
NeurIPS 2020poster

In recent years, post-hoc local instance-level and global dataset-level explainability of black-box models has received a lot of attention. Lesser attention has been given to obtaining insights at intermediate or group levels, which is a need outlined in recent works that study the challenges in rea…

Cited by 70Source ↗PDF ↗code ↗Scholar ↗
2020

Optimized Score Transformation for Fair Classification

Dennis Wei, Karthikeyan Natesan Ramamurthy, Flavio Calmon
AISTATS 2020poster

This paper considers fair probabilistic classification where the outputs of primary interest are predicted probabilities, commonly referred to as scores. We formulate the problem of transforming scores to satisfy fairness constraints while minimizing the loss in utility. The formulation can be appli…

Cited by 56Source ↗PDF ↗Scholar ↗
2019

Bias Mitigation Post-processing for Individual and Group Fairness

Pranay Kr. Lohia, Karthikeyan Natesan Ramamurthy, Manish Bhide, Diptikalyan Saha, Kush R. Varshney, Ruchir Puri
ICASSP 2019accepted

Whereas previous post-processing approaches for increasing the fairness of predictions of biased classifiers address only group fairness, we propose a method for increasing both individual and group fairness. Our novel framework includes an individual bias detector used to prioritize data samples in…

Cited by 0Source ↗Scholar ↗
2019

Topological Data Analysis of Decision Boundaries with Application to Model Selection

Karthikeyan Natesan Ramamurthy, Kush Varshney, Krishnan Mody
ICML 2019oral

We propose the labeled Cech complex, the plain labeled Vietoris-Rips complex, and the locally scaled labeled Vietoris-Rips complex to perform persistent homology inference of decision boundaries in classification tasks. We provide theoretical conditions and analysis for recovering the homology of a…

Cited by 69Source ↗PDF ↗code ↗Scholar ↗
2018

Perturbation Robust Representations of Topological Persistence Diagrams

Anirudh Som, Kowshik Thopalli, Karthikeyan Natesan Ramamurthy, Vinay Venkataraman, Ankita Shukla, Pavan Turaga
ECCV 2018poster

Topological methods for data analysis present opportunities for enforcing certain invariances of broad interest in computer vision, including view-point in activity analysis, articulation in shape analysis, and measurement invariance in non-linear dynamical modeling. The increasing success of these…

Cited by 22Source ↗PDF ↗Scholar ↗
2017

A deep learning approach to multiple kernel fusion

Huan Song, Jayaraman J. Thiagarajan, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Andreas Spanias
ICASSP 2017accepted

Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this pa…

Cited by 0Source ↗Scholar ↗
2017

Optimized Pre-Processing for Discrimination Prevention

Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, Kush R Varshney
NeurIPS 2017poster

Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling discriminat…

Cited by 1131Source ↗PDF ↗Scholar ↗
2016

Beyond L2-loss functions for learning sparse models

Karthikeyan Natesan Ramamurthy, Aleksandr Y. Aravkin, Jayaraman J. Thiagarajan
ICASSP 2016accepted

In sparse learning, the squared Euclidean distance is a popular choice for measuring the approximation quality. However, the use of other forms of parametrized loss functions, including asymmetric losses, has generated research interest. In this paper, we perform sparse learning using a broad class…

Cited by 0Source ↗Scholar ↗
2016

Consensus inference on mobile phone sensors for activity recognition

Huan Song, Jayaraman J. Thiagarajan, Karthikeyan Natesan Ramamurthy, Andreas Spanias, Pavan K. Turaga
ICASSP 2016accepted

The pervasive use of wearable sensors in activity and health monitoring presents a huge potential for building novel data analysis and prediction frameworks. In particular, approaches that can harness data from a diverse set of low-cost sensors for recognition are needed. Many of the existing approa…

Cited by 0Source ↗Scholar ↗
2015

Adaptive As-Natural-As-Possible Image Stitching

Chung-Ching Lin, Sharathchandra U. Pankanti, Karthikeyan Natesan Ramamurthy, Aleksandr Y. Aravkin
CVPR 2015poster

The goal of image stitching is to create natural-looking mosaics free of artifacts that may occur due to relative camera motion, illumination changes, and optical aberrations. In this paper, we propose a novel stitching method, that uses a smooth stitching field over the entire target image, while a…

Cited by 443Source ↗PDF ↗Scholar ↗
2015

Subspace learning using consensus on the grassmannian manifold

Jayaraman J. Thiagarajan, Karthikeyan Natesan Ramamurthy
ICASSP 2015accepted

High-dimensional structure of data can be explored and task-specific representations can be obtained using manifold learning and low-dimensional embedding approaches. However, the uncertainties in data and the sensitivity of the algorithms to parameter settings, reduce the reliability of such repres…

Cited by 0Source ↗Scholar ↗