1 code implementation • 19 Nov 2023 • Rahul Madhavan, Kahini Wadhawan
Existing methods for the attribute control task in Language Models (LMs) check for the co-occurrence of words in a sentence with the attribute of interest, and control for them.
no code implementations • 1 Jun 2023 • Rahul Madhavan, Rishabh Garg, Kahini Wadhawan, Sameep Mehta
Our experiments show that CFL achieves such a detoxification without much impact on the model perplexity.
no code implementations • 8 May 2023 • Ayush Sawarni, Rahul Madhavan, Gaurav Sinha, Siddharth Barman
We study the causal bandit problem that entails identifying a near-optimal intervention from a specified set $A$ of (possibly non-atomic) interventions over a given causal graph.
no code implementations • 1 Nov 2021 • Rahul Madhavan, Aurghya Maiti, Gaurav Sinha, Siddharth Barman
We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards.
no code implementations • 15 Apr 2021 • Rahul Madhavan, Hemanta Makwana
To speed up convergence in our algorithm, we introduce an adaptive step-size based on the curvature of the iterate convergence path -- a novelty that may be useful in more general optimization contexts as well.
1 code implementation • 12 Apr 2017 • Rahul Madhavan, Ankit Baraskar
We have created a framework for analyzing subscription based businesses in terms of a unified metric which we call SCV (single customer value).