Publications (191)
FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks
Bill Yuchen Lin, Chaoyang He, Zihang Zeng +7
Increasing concerns and regulations about data privacy and sparsity necessitate the study of privacy-preserving, decentralized learning methods for natural language processing (NLP…
FedMultimodal: A Benchmark For Multimodal Federated Learning
Tiantian Feng, Digbalay Bose, Tuo Zhang +6
Over the past few years, Federated Learning (FL) has become an emerging machine learning technique to tackle data privacy challenges through collaborative training. In the Federate…
An End-to-End Assurance Framework for AI/ML Workloads in Datacenters
Jit Gupta, Tarun Banka, Rahul Gupta +2
Modern machine learning workloads such as large language model training, fine-tuning jobs are highly distributed and span across hundreds of systems with multiple GPUs. Job complet…
Harnessing Orbital Hall Effect in Spin-Orbit Torque MRAM
Rahul Gupta, Chloé Bouard, Fabian Kammerbauer +6
Spin-Orbit Torque (SOT) Magnetic Random-Access Memory (MRAM) devices offer improved power efficiency, nonvolatility, and performance compared to static RAM, making them ideal, for…
When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
Yuting Ning, Jaylen Jones, Zhehao Zhang +5
Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such m…
Quantum information spreading in inhomogeneous spin ensembles
Rahul Gupta, Florian Mintert, Himadri Shekhar Dhar
We present a Krylov space based theoretical framework for modeling inhomogeneous spin ensembles with arbitrary distributions of spin frequencies and couplings. The framework is the…
Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development
Sattvik Sahai, Prasoon Goyal, Michael Johnston +13
AI systems for software development are rapidly gaining prominence, yet significant challenges remain in ensuring their safety. To address this, Amazon launched the Trusted AI trac…
Non-reciprocity in magnon mediated charge-spin-orbital current interconversion
José Omar Ledesma-Martin, Edgar Galindez-Ruales, Sachin Krishnia +9
In magnetic systems, angular momentum is carried by spin and orbital degrees of freedom. Nonlocal devices, comprising heavy-metal nanowires on magnetic insulators like yttrium iron…
Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning
Yixin Wan, Anil Ramakrishna, Kai-Wei Chang +2
Large Language Model (LLM) unlearning has recently gained significant attention, driven by the need to remove unwanted information, such as private, sensitive, or copyrighted conte…
SWAN: Semantic Watermarking with Abstract Meaning Representation
Ziping Ye, Gourab Dey, Christos Christodoulopoulos +7
We introduce SWAN (Semantic Watermarking with Abstract Meaning Representation), a novel framework that embeds watermark signatures into the semantic structure of a sentence using A…
SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models
Anil Ramakrishna, Yixin Wan, Xiaomeng Jin +6
We introduce SemEval-2025 Task 4: unlearning sensitive content from Large Language Models (LLMs). The task features 3 subtasks for LLM unlearning spanning different use cases: (1)…
Exploring Origin of Ultra-Long Gamma-ray Bursts: Lessons from GRB 221009A
Amit Kumar Ror, Rahul Gupta, Amar Aryan +4
The brightest Gamma-ray burst (GRB) ever, GRB 221009A, displays ultra-long GRB (ULGRB) characteristics, with a prompt emission duration exceeding 1000 s. To constrain the origin an…
Probing into emission mechanisms of GRB 190530A using time-resolved spectra and polarization studies: Synchrotron Origin?
Rahul Gupta, S. Gupta, T. Chattopadhyay +47
Multi-pulsed GRB 190530A, detected by the GBM and LAT onboard \fermi, is the sixth most fluent GBM burst detected so far. This paper presents the timing, spectral, and polarimetric…
On evaluating CNN representations for low resource medical image classification
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. However…
Time-resolved spectro-polarimetric analysis of extremely bright GRB 230307A: Possible Evidence of evolution from photospheric to synchrotron dominated emission
Soumya Gupta, Rahul Gupta, Tanmoy Chattopadhayay +11
The radiation mechanisms powering Gamma-ray bursts (GRBs) and their physical processes remain one of the unresolved questions in high-energy astrophysics. Spectro-polarimetric obse…
X-ray and gamma-ray timing of GRB 180720B, GRB 181222B, GRB 211211A and GRB 220910A observed with Fermi and ASIM
M. D. Caballero-Garcia, E. Gogus, J. Navarro-Gonzalez +20
We present a timing study of the gamma and X-ray observations and analysis of a sample of bright gamma-ray bursts (GRBs; i.e. GRB 180720B, GRB 181222B, GRB 211211A and GRB 220910A)…
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Umang Gupta, Jwala Dhamala, Varun Kumar +7
Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings. However,…
Motivic invariants of symmetric powers of curves
Rahul Gupta
We study the structure of various invariants of the symmetric powers of a smooth projective curve in terms of that of the Jacobian of the curve. We generalise the results of Macdon…
Deep Learning for Bug-Localization in Student Programs
Rahul Gupta, Aditya Kanade, Shirish Shevade
Providing feedback is an integral part of teaching. Most open online courses on programming make use of automated grading systems to support programming assignments and give real-t…
Single device offset-free magnetic field sensing principle with tunable sensitivity and linear range based on spin-orbit-torques
Sabri Koraltan, Christin Schmitt, Florian Bruckner +12
We propose a novel device concept using spin-orbit-torques to realize a magnetic field sensor, where we eliminate the sensor offset using a differential measurement concept. We der…
Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Ninareh Mehrabi, Palash Goyal, Apurv Verma +7
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions…
Generalized Collective Inference with Symmetric Clique Potentials
Rahul Gupta, Sunita Sarawagi, Ajit A. Diwan
Collective graphical models exploit inter-instance associative dependence to output more accurate labelings. However existing models support very limited kind of associativity whic…
Self-Contradictory Reasoning Evaluation and Detection
Ziyi Liu, Soumya Sanyal, Isabelle Lee +4
In a plethora of recent work, large language models (LLMs) demonstrated impressive reasoning ability, but many proposed downstream reasoning tasks only focus on final answers. Two…
Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification
Tao Meng, Ninareh Mehrabi, Palash Goyal +6
We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-l…
PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges
Swastik Roy, Rajkumar Pujari, Tharindu Kumarage +5
LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric asking for a response to be `…
Multiwavelength Observations of Gamma Ray Bursts
Rahul Gupta
Gamma-ray bursts (GRBs) are fascinating sources studied in modern astronomy. They are extremely luminous electromagnetic explosions in the Universe observed from cosmological dista…
Towards classification parity across cohorts
Aarsh Patel, Rahul Gupta, Mukund Harakere +3
Recently, there has been a lot of interest in ensuring algorithmic fairness in machine learning where the central question is how to prevent sensitive information (e.g. knowledge a…
An Efficient DP-SGD Mechanism for Large Scale NLP Models
Christophe Dupuy, Radhika Arava, Rahul Gupta +1
Recent advances in deep learning have drastically improved performance on many Natural Language Understanding (NLU) tasks. However, the data used to train NLU models may contain pr…
Itinerant Orbital Hall Effect Mechanism Leading to Large Negative Orbital Torques from Light Metal Vanadium
Nikhil Vijayan, Durgesh Kumar, Ao Du +13
The orbital Hall effect (OHE) has attracted significant attention for developing energy-efficient electronic devices. However, utilizing it in fast, low-power devices requires an e…
Relative -theory via 0-cycles in finite characteristic
Rahul Gupta, Amalendu Krishna
Let be a regular semi-local ring, essentially of finite type over an infinite perfect field of characteristic . We show that the cycle class map with modulus from an e…
Recent observations of peculiar Gamma-ray bursts using 3.6 m Devasthal Optical Telescope (DOT)
Rahul Gupta, S. B. Pandey, Amit K. Ror +2
India has been actively involved in the follow-up observations of optical afterglows of gamma-ray bursts (GRBs) for more than two decades, using the country's meter-class facilitie…
Core-collapse supernova from a possible progenitor star of 100 M
Amar Aryan, Shashi Bhushan Pandey, Abhay Pratap Yadav +3
In this work, we study the synthetic explosions of a massive star. We take a 100 M zero--age main--sequence (ZAMS) star and evolve it until the onset of core-collapse usi…
Large Language Model-driven Analysis of General Coordinates Network (GCN) Circulars
Vidushi Sharma, Ronit Agarwala, Judith L. Racusin +9
The General Coordinates Network (GCN) is NASA's time-domain and multimessenger alert system. GCN distributes two data products: automated "Notices" and human-generated "Circulars"…
Direct Observation of Unusual Interfacial Dzyaloshinskii-Moriya Interaction in Graphene/NiFe/Ta Heterostructure
Avinash Kumar Chaurasiya, Akash Kumar, Rahul Gupta +3
Graphene/ferromagnet interface promises a plethora of new science and technology. The interfacial Dzyaloshinskii Moriya interaction (iDMI) is essential for stabilizing chiral spin…
S&P 500 Stock's Movement Prediction using CNN
Rahul Gupta
This paper is about predicting the movement of stock consist of S&P 500 index. Historically there are many approaches have been tried using various methods to predict the stock mov…
Faithful Model Evaluation for Model-Based Metrics
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 re…
DECOR: Auditing LLM Deception via Information Manipulation Theory
Linyue Cai, Samuel Yeh, Jwala Dhamala +2
Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such behavior difficult to detec…
Arithmetic Cycles with Modulus
Souvik Goswami, Rahul Gupta
We add analytic components to algebraic cycles with modulus and define an arithmetic Chow group with modulus that resembles the classical arithmetic Chow groups by Gillet and SoulÃ…
CoFeAl full Heusler compound based spintronic terahertz emitter
Rahul Gupta, Sajid Husain, Ankit Kumar +3
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 lay…
A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models
Rahul Gupta, Abhinav Mohanty, Payal Motwani +8
The paper introduces a Threshold Exceedance Criteria (TEC) framework to systematically evaluate whether frontier language models increase a non‑expert's ability to plan chemical, b…
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
Tharindu Kumarage, Lisa Bauer, Yao Ma +7
As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks w…
Extremely luminous optical afterglow of an energetic gamma-ray burst GRB 230204B
Rahul Gupta, Judith Racusin, Vladimir Lipunov +47
Robotic telescope networks play an important role in capturing early and bright optical afterglows, providing critical insights into the energetics and emission mechanisms of GRBs.…
Ramified class field theory and duality over finite fields
Rahul Gupta, Amalendu Krishna
We prove a duality theorem for the -adic etale motivic cohomology of a variety which is the complement of a divisor on a smooth projective variety over $\F_p$. This extends…
An ADMM-based Coordination and Control Strategy for PV and Storage to Dispatch Stochastic Prosumers: Theory and Experimental Validation
Rahul Gupta, Fabrizio Sossan, Enrica Scolari +4
This paper describes a two-layer control and coordination framework for distributed energy resources. The lower layer is a real-time model predictive control (MPC) executed at 10 s…
Kaleidoscopic Teaming in Multi Agent Simulations
Ninareh Mehrabi, Tharindu Kumarage, Kai-Wei Chang +2
Warning: This paper contains content that may be inappropriate or offensive. AI agents have gained significant recent attention due to their autonomous tool usage capabilities and…
Sensing atomic superfluid rotation beyond the standard quantum limit
Rahul Gupta, Pardeep Kumar, Rina Kanamoto +2
Atomic superfluids formed using Bose-Einstein condensates (BECs) in a ring trap are currently being investigated in the context of superfluid hydrodynamics, quantum sensing and mat…
JAB: Joint Adversarial Prompting and Belief Augmentation
Ninareh Mehrabi, Palash Goyal, Anil Ramakrishna +6
With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance. Here we introduce a joint…
Federated Learning with Noisy User Feedback
Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin +5
Machine Learning (ML) systems are getting increasingly popular, and drive more and more applications and services in our daily life. This has led to growing concerns over user priv…
Prompt emission and early optical afterglow of VHE detected GRB 201015A and GRB 201216C: onset of the external forward shock
Amit Kumar Ror, Rahul Gupta, Martin JelÃnek +19
We present a detailed prompt emission and early optical afterglow analysis of the two very high energy (VHE) detected bursts GRB 201015A and GRB 201216C, and their comparison with…
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
Linxin Song, Xuwei Ding, Jieyu Zhang +6
Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Und…
Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
Elan Markowitz, Anil Ramakrishna, Jwala Dhamala +5
Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. However, KGs and LLMs are ofte…
SN 2010kd: Photometric and Spectroscopic Analysis of a Slow-Decaying Superluminous Supernova
Amit Kumar, Shashi Bhushan Pandey, Reka Konyves-Toth +21
This paper presents data and analysis of SN 2010kd, a low-redshift () H-deficient superluminous supernova (SLSN), based on ultraviolet/optical photometry and optical spe…
Multi-VALUE: A Framework for Cross-Dialectal English NLP
Caleb Ziems, William Held, Jingfeng Yang +3
Dialect differences caused by regional, social, and economic factors cause performance discrepancies for many groups of language technology users. Inclusive and equitable language…
Coordinated Replay Sample Selection for Continual Federated Learning
Jack Good, Jimit Majmudar, Christophe Dupuy +5
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…
Fast Intent Classification for Spoken Language Understanding
Akshit Tyagi, Varun Sharma, Rahul Gupta +4
Spoken Language Understanding (SLU) systems consist of several machine learning components operating together (e.g. intent classification, named entity recognition and resolution).…
Establishing Best Practices for Building Rigorous Agentic Benchmarks
Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun +22
Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to e…
Cavity Optomechanical Quantum Memory for Twisted Photons Using a Ring BEC
Nilamoni Daloi, Rahul Gupta, Aritra Ghosh +3
We theoretically propose a photonic orbital angular momentum (OAM) quantum memory platform based on an atomic Bose-Einstein condensate confined in a ring trap and placed inside a F…
Canary Extraction in Natural Language Understanding Models
Rahil Parikh, Christophe Dupuy, Rahul Gupta
Natural Language Understanding (NLU) models can be trained on sensitive information such as phone numbers, zip-codes etc. Recent literature has focused on Model Inversion Attacks (…
Multi-wavelength study of the luminous GRB 210619B observed with Fermi and ASIM
M. D. Caballero-GarcÃa, Rahul Gupta, S. B. Pandey +28
We report on detailed multi-wavelength observations and analysis of the very bright and long GRB 210619B, detected by the Atmosphere-Space Interactions Monitor (ASIM) installed on…
Deep Reinforcement Learning for Programming Language Correction
Rahul Gupta, Aditya Kanade, Shirish Shevade
Novice programmers often struggle with the formal syntax of programming languages. To assist them, we design a novel programming language correction framework amenable to reinforce…
LUME: LLM Unlearning with Multitask Evaluations
Anil Ramakrishna, Yixin Wan, Xiaomeng Jin +6
Unlearning aims to remove copyrighted, sensitive, or private content from large language models (LLMs) without a full retraining. In this work, we develop a multi-task unlearning b…
Identification of orbital pumping from spin pumping and rectification effects
Nils Keller, Arnab Bose, Nozomi Soya +9
The recently predicted mechanism of orbital pumping enables the generation of pure orbital current from a precessing ferromagnet (FM) without the need for electrical current inject…
A Partial Order Reduction Technique for Event-driven Multi-threaded Programs
Pallavi Maiya, Rahul Gupta, Aditya Kanade +1
Event-driven multi-threaded programming is fast becoming a preferred style of developing efficient and responsive applications. In this concurrency model, multiple threads execute…
Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models
Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna +2
Artificial Intelligence have profoundly transformed the technological landscape in recent years. Large Language Models (LLMs) have demonstrated impressive abilities in reasoning, t…
Automatic Discovery of Novel Intents & Domains from Text Utterances
Nikhita Vedula, Rahul Gupta, Aman Alok +1
One of the primary tasks in Natural Language Understanding (NLU) is to recognize the intents as well as domains of users' spoken and written language utterances. Most existing rese…
An Intermediate Luminosity GRB 210210A: The early onset of the external forward shock in the X-ray?
Rahul Gupta, A. K. Ror, S. B. Pandey +5
We have analyzed the prompt and afterglow characteristics of the intermediate luminosity burst ``GRB 210210A". Our prompt emission analysis indicates that GRB 210210A is among the…
GRB 210217A: A short or a long GRB?
Dimple, Kuntal Misra, Ankur Ghosh +6
Gamma-ray bursts are traditionally classified as short and long bursts based on their value (the time interval during which an instrument observes to of g…
GRB 140102A: Insight into Prompt Spectral Evolution and Early Optical Afterglow Emission
Rahul Gupta, S. R. Oates, S. B. Pandey +38
We present and perform a detailed analysis of multi-wavelength observations of \thisgrb, an optical bright GRB with an observed reverse shock (RS) signature. Observations of this G…
Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench
Ziyi Liu, Priyanka Dey, Jen-tse Huang +6
Cultural Intelligence (CQ) refers to the ability to understand unfamiliar cultural contexts, a crucial skill for large language models (LLMs) to effectively engage with globally di…
Torsion in abelian fundamental group and its application
Rahul Gupta, Jitendra Rathore
We prove that the torsion subgroup of the abelian fundamental group is finite for a regular geometrically integral projective variety over a local field. We also study the structur…
4K4K CCD Imager for the 3.6m DOT: Recent up-gradations and results
S. B. Pandey, Amit Kumar, B. K. Reddy +6
The 4K4K CCD Imager is the first light instrument for the 3.6m Devasthal Optical Telescope and is producing broad-band imaging observations of many Galactic and extra-galac…
Model-less Robust Voltage Control in Active Distribution Networks using Sensitivity Coefficients Estimated from Measurements
Rahul Gupta, Fabrizio Sossan, Mario Paolone
Measurement-rich power distribution networks may enable distribution system operators (DSOs) to adopt model-less and measurement-based monitoring and control of distributed energy…
Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
Huihan Li, You Chen, Siyuan Wang +4
Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about the extent to which their success relies on memo…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Evolution of Rotating 25 M Population III star: Physical Properties and Resulting Supernovae
Amar Aryan, Shashi Bhushan Pandey, Rahul Gupta +1
In this Letter, we report the outcomes of 1-D modelling of a rotating 25 M zero-age main-sequence Population III star up to the stage of the onset of core collapse. Rapid…
A decomposition theorem for 0-cycles and applications
Rahul Gupta, Amalendu Krishna, Jitendra Rathore
We prove a decomposition theorem for the cohomological Chow group of 0-cycles on the double of a quasi-projective -scheme over a field along a closed subscheme, in terms of th…
Retrieval-Augmented Multi-Agent System for Rapid Statement of Work Generation
Amulya Suravarjhula, Rashi Chandrashekhar Agrawal, Sakshi Jayesh Patel +1
Drafting a Statement of Work (SOW) is a vital part of business and legal projects. It outlines key details like deliverables, timelines, responsibilities, and legal terms. However,…
SN 2020ank: a bright and fast-evolving H-deficient superluminous supernova
Amit Kumar, Brajesh Kumar, S. B. Pandey +7
We investigate the observational properties of a hydrogen-deficient superluminous supernova (SLSN) SN 2020ank (at z = 0.2485), with the help of early phase observations carried out…
A multi-wavelength analysis of a collection of short-duration GRBs observed between 2012-2015
S. B. Pandey, Y. Hu, A. J. Castro-Tirado +71
We investigate the prompt emission and the afterglow properties of short duration gamma-ray burst (sGRB) 130603B and another eight sGRB events during 2012-2015, observed by several…
MUTANT: A Multi-sentential Code-mixed Hinglish Dataset
Rahul Gupta, Vivek Srivastava, Mayank Singh
The multi-sentential long sequence textual data unfolds several interesting research directions pertaining to natural language processing and generation. Though we observe several…
ADePT: Auto-encoder based Differentially Private Text Transformation
Satyapriya Krishna, Rahul Gupta, Christophe Dupuy
Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
Investigating Temporal Features in Swift GRB Afterglows: A Comparative Study of UVOT and XRT Data
Amit K. Ror, S. B. Pandey, S. R. Oates +4
This study presents a statistical analysis of optical light curves (LCs) of 200 UVOT-detected GRBs from 2005 to 2018. We have categorised these LCs based on their distinct morpholo…
Strategic Electric Distribution Network Sensing via Spectral Bandits
Samuel Talkington, Rahul Gupta, Richard Asiamah +2
Despite their wide-scale deployment and ability to make accurate high-frequency voltage measurements, communication network limitations have largely precluded the use of smart mete…
On Enhancing Speech Emotion Recognition using Generative Adversarial Networks
Saurabh Sahu, Rahul Gupta, Carol Espy-Wilson
Generative Adversarial Networks (GANs) have gained a lot of attention from machine learning community due to their ability to learn and mimic an input data distribution. GANs consi…
Toward Informal Language Processing: Knowledge of Slang in Large Language Models
Zhewei Sun, Qian Hu, Rahul Gupta +2
Recent advancement in large language models (LLMs) has offered a strong potential for natural language systems to process informal language. A representative form of informal langu…
Inferring object rankings based on noisy pairwise comparisons from multiple annotators
Rahul Gupta, Shrikanth Narayanan
Ranking a set of objects involves establishing an order allowing for comparisons between any pair of objects in the set. Oftentimes, due to the unavailability of a ground truth of…
On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
Yang Trista Cao, Yada Pruksachatkun, Kai-Wei Chang +4
Multiple metrics have been introduced to measure fairness in various natural language processing tasks. These metrics can be roughly categorized into two categories: 1) \emph{extri…
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna +6
Safety reasoning is a recent paradigm where LLMs reason over safety policies before generating responses, thereby mitigating limitations in existing safety measures such as over-re…
Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks
Ansel MacLaughlin, Jwala Dhamala, Anoop Kumar +3
Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-…
Differentially Private Decoding in Large Language Models
Jimit Majmudar, Christophe Dupuy, Charith Peris +3
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-traine…
FLIRT: Feedback Loop In-context Red Teaming
Ninareh Mehrabi, Palash Goyal, Christophe Dupuy +6
Warning: this paper contains content that may be inappropriate or offensive. As generative models become available for public use in various applications, testing and analyzing vul…
Progenitor mass constraints for the type Ib intermediate-luminosity SN 2015ap and the highly extinguished SN 2016bau
Amar Aryan, S. B. Pandey, WeiKang Zheng +21
Photometric and spectroscopic analyses of the intermediate-luminosity Type Ib supernova (SN) 2015ap and of the heavily reddened Type Ib SN~2016bau are discussed. Photometric proper…
ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification
Manoj Kumar, Varun Kumar, Hadrien Glaude +3
Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this pro…
Measurement-based/Model-less Estimation of Voltage Sensitivity Coefficients by Feedforward and LSTM Neural Networks in Power Distribution Grids
Robin Henry, Rahul Gupta
The increasing adoption of measurement units in electrical power distribution grids has enabled the deployment of data-driven and measurement-based control schemes. Such schemes re…
Cavity-Driven Multispectral Gain for High-Sensitivity NV Center Magnetometers
Himanshu Kumar, Rahul Gupta, Saikat Ghosh +2
We report a cavity-enabled solid-state magnetometer based on an NV ensemble coupled with a dielectric cavity, achieving 12 pT/ sensitivity and a nearly threefold ga…
A Novel Method to Calculate Click Through Rate for Sponsored Search
Rahul Gupta, Gitansh Khirbat, Sanjay Singh
Sponsored search adopts generalized second price (GSP) auction mechanism which works on the concept of pay per click which is most commonly used for the allocation of slots in the…
Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
Fei Wang, Ninareh Mehrabi, Palash Goyal +3
Data is a crucial element in large language model (LLM) alignment. Recent studies have explored using LLMs for efficient data collection. However, LLM-generated data often suffers…
Time Temperature Superposition in Soft Glassy Materials
Rahul Gupta, Bharat Baldewa, Yogesh M. Joshi
Soft glassy materials are out of thermodynamic equilibrium and show time dependent slowing down of the relaxation dynamics. Under such situation these materials follow Boltzmann su…
Data augmentation for low resource sentiment analysis using generative adversarial networks
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. In cases where data is inadequate fo…