Arrow Research search

Author name cluster

Mohit Sharma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers
1 author row

Possible papers

6

NeurIPS Conference 2025 Conference Paper

On Optimal Steering to Achieve Exact Fairness

  • Mohit Sharma
  • Amit Deshpande
  • Chiranjib Bhattacharyya
  • Rajiv Ratn Shah

To fix the `bias in, bias out' problem in fair machine learning, it is important to steer feature distributions of data or internal representations of Large Language Models (LLMs) to \emph{ideal} ones that guarantee group-fair outcomes. Previous work on fair generative models and representation steering could greatly benefit from provable fairness guarantees on the model output. We define a distribution as \emph{ideal} if the minimizer of any cost-sensitive risk on it is guaranteed to have exact group-fair outcomes (e. g. , demographic parity, equal opportunity)---in other words, it has no fairness-utility trade-off. We formulate an optimization program for optimal steering by finding the nearest \emph{ideal} distribution in KL-divergence, and provide efficient algorithms for it when the underlying distributions come from well-known parametric families (e. g. , normal, log-normal). Empirically, our optimal steering techniques on both synthetic and real-world datasets improve fairness without diminishing utility (and sometimes even improve utility). We demonstrate affine steering of LLM representations to reduce bias in multi-class classification, e. g. , occupation prediction from a short biography in Bios dataset (De-Arteaga et al. ). Furthermore, we steer internal representations of LLMs towards desired outputs so that it works equally well across different groups.

AAAI Conference 2021 Conference Paper

Inverse Reinforcement Learning with Explicit Policy Estimates

  • Navyata Sanghvi
  • Shinnosuke Usami
  • Mohit Sharma
  • Joachim Groeger
  • Kris Kitani

Various methods for solving the inverse reinforcement learning (IRL) problem have been developed independently in machine learning and economics. In particular, the method of Maximum Causal Entropy IRL is based on the perspective of entropy maximization, while related advances in the field of economics instead assume the existence of unobserved action shocks to explain expert behavior (Nested Fixed Point Algorithm, Conditional Choice Probability method, Nested Pseudo-Likelihood Algorithm). In this work, we make previously unknown connections between these related methods from both fields. We achieve this by showing that they all belong to a class of optimization problems, characterized by a common form of the objective, the associated policy and the objective gradient. We demonstrate key computational and algorithmic differences which arise between the methods due to an approximation of the optimal soft value function, and describe how this leads to more efficient algorithms. Using insights which emerge from our study of this class of optimization problems, we identify various problem scenarios and investigate each method’s suitability for these problems.

AAAI Conference 2020 Short Paper

Analysis of Parliamentary Debate Transcripts Using Community-Based Graphical Approaches (Student Abstract)

  • Anjali Bhavan
  • Mohit Sharma
  • Ramit Sawhney
  • Rajiv Ratn Shah

Gauging political sentiments and analyzing stances of elected representatives pose an important challenge today, and one with wide-ranging ramifications. Community-based analysis of parliamentary debate sentiments could pave a way for better insights into the political happenings of a nation and help in keeping the voters informed. Such analysis could be given another dimension by studying the underlying connections and networks in such data. We present a sentiment classification method for UK Parliament debate transcripts, which is a combination of a graphical method based on DeepWalk embeddings and text-based analytical methods. We also present proof for our hypothesis that parliamentarians with similar voting patterns tend to deliver similar speeches. We also provide some further avenues and future work towards the end.

IJCAI Conference 2020 Conference Paper

IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL

  • Nirbhay Modhe
  • Prithvijit Chattopadhyay
  • Mohit Sharma
  • Abhishek Das
  • Devi Parikh
  • Dhruv Batra
  • Ramakrishna Vedantam

We propose a novel framework to identify sub-goals useful for exploration in sequential decision making tasks under partial observability. We utilize the variational intrinsic control framework (Gregor et. al. , 2016) which maximizes empowerment -- the ability to reliably reach a diverse set of states and show how to identify sub-goals as states with high necessary option information through an information theoretic regularizer. Despite being discovered without explicit goal supervision, our sub-goals provide better exploration and sample complexity on challenging grid-world navigation tasks compared to supervised counterparts in prior work.

AAAI Conference 2020 Short Paper

SpotFake+: A Multimodal Framework for Fake News Detection via Transfer Learning (Student Abstract)

  • Shivangi Singhal
  • Anubha Kabra
  • Mohit Sharma
  • Rajiv Ratn Shah
  • Tanmoy Chakraborty
  • Ponnurangam Kumaraguru

In recent years, there has been a substantial rise in the consumption of news via online platforms. The ease of publication and lack of editorial rigour in some of these platforms have further led to the proliferation of fake news. In this paper, we study the problem of detecting fake news on the FakeNewsNet repository, a collection of full length articles along with associated images. We present SpotFake+, a multimodal approach that leverages transfer learning to capture semantic and contextual information from the news articles and its associated images and achieves the better accuracy for fake news detection. To the best of our knowledge, this is the first work that performs a multimodal approach for fake news detection on a dataset that consists of full length articles. It outperforms the performance shown by both single modality and multiple-modality models. We also release the pretrained model for the benefit of the community.

NeurIPS Conference 2010 Conference Paper

Decoding Ipsilateral Finger Movements from ECoG Signals in Humans

  • Yuzong Liu
  • Mohit Sharma
  • Charles Gaona
  • Jonathan Breshears
  • Jarod Roland
  • Zachary Freudenburg
  • Eric Leuthardt
  • Kilian Weinberger

Several motor related Brain Computer Interfaces (BCIs) have been developed over the years that use activity decoded from the contralateral hemisphere to operate devices. Many recent studies have also talked about the importance of ipsilateral activity in planning of motor movements. For successful upper limb BCIs, it is important to decode finger movements from brain activity. This study uses ipsilateral cortical signals from humans (using ECoG) to decode finger movements. We demonstrate, for the first time, successful finger movement detection using machine learning algorithms. Our results show high decoding accuracies in all cases which are always above chance. We also show that significant accuracies can be achieved with the use of only a fraction of all the features recorded and that these core features also make sense physiologically. The results of this study have a great potential in the emerging world of motor neuroprosthetics and other BCIs.