no code implementations • NAACL (ACL) 2022 • Manoj Kumar, Yuval Merhav, Haidar Khan, Rahul Gupta, Anna Rumshisky, Wael Hamza
Use of synthetic data is rapidly emerging as a realistic alternative to manually annotating live traffic for industry-scale model building.
no code implementations • 15 Feb 2025 • Elan Markowitz, Anil Ramakrishna, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
However, these approaches fail to produce edits that account for associated contextual information.
no code implementations • 27 Nov 2024 • Sathwik Karnik, Zhang-Wei Hong, Nishant Abhangi, Yen-Chen Lin, Tsun-Hsuan Wang, Christophe Dupuy, Rahul Gupta, Pulkit Agrawal
Language-conditioned robot models have the potential to enable robots to perform a wide range of tasks based on natural language instructions.
no code implementations • 28 Oct 2024 • Samuel Talkington, Rahul Gupta, Richard Asiamah, Paprapee Buason, Daniel K. Molzahn
Despite their wide-scale deployment and ability to make accurate high-frequency voltage measurements, communication network limitations have largely precluded the use of smart meters for real-time monitoring purposes in electric distribution systems.
1 code implementation • 7 Oct 2024 • Fei Wang, Ninareh Mehrabi, Palash Goyal, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
Starting from a set of pre-defined principles in hand, Data Advisor monitors the status of the generated data, identifies weaknesses in the current dataset, and advises the next iteration of data generation accordingly.
no code implementations • 7 Oct 2024 • Tao Meng, Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Aram Galstyan, Richard Zemel, Kai-Wei Chang, Rahul Gupta, Charith Peris
We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control.
1 code implementation • 31 Jul 2024 • Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi, Charith Peris, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge.
1 code implementation • 29 May 2024 • Isha Chaudhary, Qian Hu, Manoj Kumar, Morteza Ziyadi, Rahul Gupta, Gagandeep Singh
A certificate consists of high-confidence bounds on the probability of unbiased LLM responses for any set of prompts mentioning various demographic groups, sampled from a distribution.
no code implementations • 27 Apr 2024 • Tiantian Feng, Xuan Shi, Rahul Gupta, Shrikanth S. Narayanan
Automatic Speech Understanding (ASU) aims at human-like speech interpretation, providing nuanced intent, emotion, sentiment, and content understanding from speech and language (text) content conveyed in speech.
1 code implementation • 2 Apr 2024 • Zhewei Sun, Qian Hu, Rahul Gupta, Richard Zemel, Yang Xu
Our work offers a comprehensive evaluation and a high-quality benchmark on English slang based on the OpenSubtitles corpus, serving both as a publicly accessible resource and a platform for applying tools for informal language processing.
no code implementations • 3 Mar 2024 • Tiantian Feng, Anil Ramakrishna, Jimit Majmudar, Charith Peris, Jixuan Wang, Clement Chung, Richard Zemel, Morteza Ziyadi, Rahul Gupta
Federated Learning (FL) is a popular algorithm to train machine learning models on user data constrained to edge devices (for example, mobile phones) due to privacy concerns.
no code implementations • 19 Dec 2023 • Palash Goyal, Qian Hu, Rahul Gupta
Statistical significance testing is used in natural language processing (NLP) to determine whether the results of a study or experiment are likely to be due to chance or if they reflect a genuine relationship.
no code implementations • 19 Dec 2023 • Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Yuval Pinter, Rahul Gupta
Our paper is the first to link LLM misgendering to tokenization and deficient neopronoun grammar, indicating that LLMs unable to correctly treat neopronouns as pronouns are more prone to misgender.
no code implementations • 14 Dec 2023 • Robin Henry, Rahul Gupta
This work focuses on measurement-based estimation of the voltage sensitivity coefficients which can be used for voltage control.
no code implementations • 14 Dec 2023 • Rahul Gupta
The power-flow sensitivity coefficients (PFSCs) are widely used in the power system for expressing linearized dependencies between the controlled (i. e., the nodal voltages, lines currents) and control variables (e. g., active and reactive power injections, transformer tap positions, etc.).
no code implementations • 16 Nov 2023 • Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna, Jwala Dhamala, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance.
1 code implementation • 16 Nov 2023 • Ziyi Liu, Soumya Sanyal, Isabelle Lee, Yongkang Du, Rahul Gupta, Yang Liu, Jieyu Zhao
For 2), we task the state-of-the-art model GPT-4 with identifying Self-Contra reasoning and finer-grained fallacies.
no code implementations • 8 Nov 2023 • Junyi Li, Ninareh Mehrabi, Charith Peris, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta
Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented.
no code implementations • 23 Oct 2023 • Jack Good, Jimit Majmudar, Christophe Dupuy, Jixuan Wang, Charith Peris, Clement Chung, Richard Zemel, Rahul Gupta
Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learning of a model from a continual stream of data without keeping the entire history.
1 code implementation • 23 Oct 2023 • Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Frederick Wieting, Nanyun Peng, Xuezhe Ma
While recent studies have looked into the abilities of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc, there have been few studies looking into the controllability of large language models on generation tasks.
no code implementations • 8 Aug 2023 • Ninareh Mehrabi, Palash Goyal, Christophe Dupuy, Qian Hu, Shalini Ghosh, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta
In this work, we propose an automatic red teaming framework that evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation.
no code implementations • 15 Jun 2023 • Tiantian Feng, Digbalay Bose, Tuo Zhang, Rajat Hebbar, Anil Ramakrishna, Rahul Gupta, Mi Zhang, Salman Avestimehr, Shrikanth Narayanan
In order to facilitate the research in multimodal FL, we introduce FedMultimodal, the first FL benchmark for multimodal learning covering five representative multimodal applications from ten commonly used datasets with a total of eight unique modalities.
1 code implementation • 19 May 2023 • Mustafa Safa Ozdayi, Charith Peris, Jack FitzGerald, Christophe Dupuy, Jimit Majmudar, Haidar Khan, Rahil Parikh, Rahul Gupta
We present a novel approach which uses prompt-tuning to control the extraction rates of memorized content in LLMs.
no code implementations • 17 May 2023 • Anaelia Ovalle, Palash Goyal, Jwala Dhamala, Zachary Jaggers, Kai-Wei Chang, Aram Galstyan, Richard Zemel, Rahul Gupta
Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life.
no code implementations • 26 Apr 2023 • Rahul Gupta, Mario Paolone
The estimated voltage sensitivity coefficients are used to model the nodal voltages, and the control robustness is achieved by accounting for their uncertainties.
no code implementations • 23 Feb 2023 • Rahul Gupta, Vivek Srivastava, Mayank Singh
As a use case, we leverage multilingual articles from two different data sources and build a first-of-its-kind multi-sentential code-mixed Hinglish dataset i. e., MUTANT.
no code implementations • 15 Dec 2022 • Caleb Ziems, William Held, Jingfeng Yang, Jwala Dhamala, Rahul Gupta, Diyi Yang
First, we use this system to stress tests question answering, machine translation, and semantic parsing.
no code implementations • 17 Nov 2022 • Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar, Qian Hu, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Rahul Gupta
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication.
no code implementations • 31 Oct 2022 • Aman Alok, Rahul Gupta, Shankar Ananthakrishnan
Hypothesis rejection modules in both schemes reject/accept a hypothesis based on features drawn from the utterance directed to the SLU system, the associated SLU hypothesis and SLU confidence score.
no code implementations • 7 Oct 2022 • Jwala Dhamala, Varun Kumar, Rahul Gupta, Kai-Wei Chang, Aram Galstyan
We present a systematic analysis of the impact of decoding algorithms on LM fairness, and analyze the trade-off between fairness, diversity and quality.
1 code implementation • 2 Aug 2022 • Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald, Rahul Gupta, Wael Hamza, Haidar Khan, Charith Peris, Stephen Rawls, Andy Rosenbaum, Anna Rumshisky, Chandana Satya Prakash, Mukund Sridhar, Fabian Triefenbach, Apurv Verma, Gokhan Tur, Prem Natarajan
In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models on various tasks.
Ranked #14 on
Natural Language Inference
on CommitmentBank
no code implementations • 26 May 2022 • Jimit Majmudar, Christophe Dupuy, Charith Peris, Sami Smaili, Rahul Gupta, Richard Zemel
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart.
no code implementations • NAACL 2022 • Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta
Federated learning (FL) has recently emerged as a method for training ML models on edge devices using sensitive user data and is seen as a way to mitigate concerns over data privacy.
no code implementations • NAACL 2022 • Peyman Passban, Tanya Roosta, Rahul Gupta, Ankit Chadha, Clement Chung
Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques.
no code implementations • ACL 2022 • Yang Trista Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, Aram Galstyan
Multiple metrics have been introduced to measure fairness in various natural language processing tasks.
no code implementations • ACL 2022 • Rahil Parikh, Christophe Dupuy, Rahul Gupta
In this work, we present a version of such an attack by extracting canaries inserted in NLU training data.
no code implementations • Findings (ACL) 2022 • Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, Aram Galstyan
Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings.
no code implementations • ACL 2022 • Satyapriya Krishna, Rahul Gupta, Apurv Verma, Jwala Dhamala, Yada Pruksachatkun, Kai-Wei Chang
With the rapid growth in language processing applications, fairness has emerged as an important consideration in data-driven solutions.
no code implementations • 8 Feb 2022 • Christophe Dupuy, Tanya G. Roosta, Leo Long, Clement Chung, Rahul Gupta, Salman Avestimehr
In this study, we evaluate the impact of such idiosyncrasies on Natural Language Understanding (NLU) models trained using FL.
no code implementations • 11 Jan 2022 • Rahul Gupta, Fabrizio Sossan, Mario Paolone
This formulation is applied to control distributed controllable photovoltaic (PV) generation in a distribution network to restrict the voltage within prescribed limits.
no code implementations • 10 Jan 2022 • Rahul Gupta, Sherif Fahmy, Mario Paolone
Specifically, the proposed framework optimizes the dispatch plan of an upstream medium voltage (MV) grid accounting for the flexibility offered by downstream low voltage (LV) grids and the knowledge of the uncertainties of the stochastic resources.
1 code implementation • Findings (EMNLP) 2021 • Justin Payan, Yuval Merhav, He Xie, Satyapriya Krishna, Anil Ramakrishna, Mukund Sridhar, Rahul Gupta
There is an increasing interest in continuous learning (CL), as data privacy is becoming a priority for real-world machine learning applications.
no code implementations • 19 Oct 2021 • Francesco Gerini, Yihui Zuo, Rahul Gupta, Elena Vagnoni, Rachid Cherkaoui, Mario Paolone
This paper proposes and experimentally validates a joint control and scheduling framework for a grid-forming converter-interfaced BESS providing multiple services to the electrical grid.
no code implementations • 14 Jul 2021 • Christophe Dupuy, Radhika Arava, Rahul Gupta, Anna Rumshisky
However, the data used to train NLU models may contain private information such as addresses or phone numbers, particularly when drawn from human subjects.
no code implementations • Findings (ACL) 2021 • Yada Pruksachatkun, Satyapriya Krishna, Jwala Dhamala, Rahul Gupta, Kai-Wei Chang
Existing bias mitigation methods to reduce disparities in model outcomes across cohorts have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training.
1 code implementation • Findings (NAACL) 2022 • Bill Yuchen Lin, Chaoyang He, Zihang Zeng, Hulin Wang, Yufen Huang, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr
Increasing concerns and regulations about data privacy and sparsity necessitate the study of privacy-preserving, decentralized learning methods for natural language processing (NLP) tasks.
2 code implementations • EACL 2021 • Satyapriya Krishna, Rahul Gupta, Christophe Dupuy
We prove the theoretical privacy guarantee of our algorithm and assess its privacy leakage under Membership Inference Attacks(MIA) (Shokri et al., 2017) on models trained with transformed data.
no code implementations • 28 Jan 2021 • Manoj Kumar, Varun Kumar, Hadrien Glaude, Cyprien delichy, Aman Alok, Rahul Gupta
We make use of a conditional generator for data augmentation that is trained directly using the meta-learning objective and simultaneously with prototypical networks, hence ensuring that data augmentation is customized to the task.
1 code implementation • 27 Jan 2021 • Jwala Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta
To systematically study and benchmark social biases in open-ended language generation, we introduce the Bias in Open-Ended Language Generation Dataset (BOLD), a large-scale dataset that consists of 23, 679 English text generation prompts for bias benchmarking across five domains: profession, gender, race, religion, and political ideology.
no code implementations • 26 Jan 2021 • Rahul Gupta, Sajid Husain, Ankit Kumar, Rimantas Brucas, Anders Rydberg, Peter Svedlindh
To achieve a large terahertz (THz) amplitude from a spintronic THz emitter (STE), materials with 100\% spin polarisation such as Co-based Heusler compounds as the ferromagnetic layer are required.
Materials Science Mesoscale and Nanoscale Physics Other Condensed Matter Optics
no code implementations • EMNLP (insights) 2020 • Ansel MacLaughlin, Jwala Dhamala, Anoop Kumar, Sriram Venkatapathy, Ragav Venkatesan, Rahul Gupta
Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-art (SOTA) performance on variety of natural language processing and computer vision tasks, including language modeling, natural language inference, and image classification.
no code implementations • 20 Jul 2020 • Rahul Gupta, Subhajit Roy, Kuldeep S. Meel
The study of phase transition behaviour in SAT has led to deeper understanding and algorithmic improvements of modern SAT solvers.
no code implementations • 22 May 2020 • Nikhita Vedula, Rahul Gupta, Aman Alok, Mukund Sridhar
We propose a novel framework, ADVIN, to automatically discover novel domains and intents from large volumes of unlabeled data.
no code implementations • 16 May 2020 • Aarsh Patel, Rahul Gupta, Mukund Harakere, Satyapriya Krishna, Aman Alok, Peng Liu
In this research work, we aim to achieve classification parity across explicit as well as implicit sensitive features.
no code implementations • 6 May 2020 • Anil Ramakrishna, Rahul Gupta, Shrikanth Narayanan
In this work we address this by proposing a generative model for multi-dimensional annotation fusion, which models the dimensions jointly leading to more accurate ground truth estimates.
1 code implementation • 3 Dec 2019 • Akshit Tyagi, Varun Sharma, Rahul Gupta, Lynn Samson, Nan Zhuang, Zihang Wang, Bill Campbell
To address the latency and computational complexity issues, we explore a BranchyNet scheme on an intent classification scheme within SLU systems.
1 code implementation • NeurIPS 2019 • Rahul Gupta, Aditya Kanade, Shirish Shevade
In this work, we present NeuralBugLocator, a deep learning based technique, that can localize the bugs in a faulty program with respect to a failing test, without even running the program.
no code implementations • 31 Oct 2019 • Saurabh Sahu, Rahul Gupta, Carol Espy-Wilson
In this work, we experiment with variants of GAN architectures to generate feature vectors corresponding to an emotion in two ways: (i) A generator is trained with samples from a mixture prior.
no code implementations • 20 Jun 2019 • Rahul Gupta, Aman Alok, Shankar Ananthakrishnan
An OVA system consists of as many OVA models as the number of classes, providing the advantage of asynchrony, where each OVA model can be re-trained independent of other models.
no code implementations • 28 May 2019 • Rahul Gupta, Aditya Kanade, Shirish Shevade
To localize the bugs, we analyze the trained network using a state-of-the-art neural prediction attribution technique and see which lines of the programs make it predict the test outcomes.
no code implementations • 26 Mar 2019 • Taruna Agrawal, Rahul Gupta, Shrikanth Narayanan
Convolutional Neural Networks (CNNs) have revolutionized performances in several machine learning tasks such as image classification, object tracking, and keyword spotting.
no code implementations • 18 Feb 2019 • Rahul Gupta
Sentiment analysis is a task that may suffer from a lack of data in certain cases, as the datasets are often generated and annotated by humans.
no code implementations • 31 Oct 2018 • Su Wang, Rahul Gupta, Nancy Chang, Jason Baldridge
Paraphrasing is rooted in semantics.
no code implementations • 25 Sep 2018 • Chengwei Su, Rahul Gupta, Shankar Ananthakrishnan, Spyros Matsoukas
An ideal re-ranker will exhibit the following two properties: (a) it should prefer the most relevant hypothesis for the given input as the top hypothesis and, (b) the interpretation scores corresponding to each hypothesis produced by the re-ranker should be calibrated.
no code implementations • 18 Jun 2018 • Saurabh Sahu, Rahul Gupta, Carol Espy-Wilson
GANs consist of a discriminator and a generator working in tandem playing a min-max game to learn a target underlying data distribution; when fed with data-points sampled from a simpler distribution (like uniform or Gaussian distribution).
no code implementations • 7 Jun 2018 • Rahul Gupta, Saurabh Sahu, Carol Espy-Wilson, Shrikanth Narayanan
Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event.
no code implementations • 6 Jun 2018 • Saurabh Sahu, Rahul Gupta, Ganesh Sivaraman, Wael Abd-Almageed, Carol Espy-Wilson
Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition.
1 code implementation • 31 Jan 2018 • Rahul Gupta, Aditya Kanade, Shirish Shevade
Novice programmers often struggle with the formal syntax of programming languages.
Ranked #4 on
Program Repair
on DeepFix
2 code implementations • 19 Oct 2017 • Michael Ringgaard, Rahul Gupta, Fernando C. N. Pereira
We describe SLING, a framework for parsing natural language into semantic frames.
1 code implementation • 4 Feb 2017 • Rahul Gupta, Soham Pal, Aditya Kanade, Shirish Shevade
The problem of automatically fixing programming errors is a very active research topic in software engineering.
no code implementations • 13 Dec 2016 • Rahul Gupta, Shrikanth Narayanan
In this work, we propose Expectation-Maximization (EM) based algorithms that rely on the judgments from multiple annotators and the object attributes for inferring the latent ground truth.