Aman Chadha • Research

About • Works • Resume • Research

Research

Citations: 2141 • h-index: 21 • Google Scholar

Media Coverage

• AIM (Personal Profile; ECIR 2024 MedSumm Paper; Gaussian Adaptive Attention Paper; State of LLMs; Indic LLMs; CIKM 2024 Auditing LLMs Paper)
• The Washington Post (EMNLP 2023 LLM Hallucinations Paper)
• New Scientist (LLM Socioeconomic Biases Paper)
• YourStory (Personal Profile)
• Wikipedia (LLM Hallucination Survey Paper)
• Nature (EMNLP 2023 LLM Hallucinations Paper)

Talks/Tutorials

• University of Cincinnati/Cincinnati Children's Hospital: GenAI in Healthcare | Sept 2024 (Talk)
• University of Maryland, Baltimore County: Grounding LLMs | Sept 2024 (Talk, Slides)
• University of South Carolina: Agentic AI | Nov 2024 (Talk, Slides)
• San Diego State University: Transformer Architecture | Nov 2024 (Talk, Slides)
• San Diego State University: Reasoning LLMs | Faculty Lecture; April 2025 (Talk, Slides)
• Worcester Polytechnic Institute: Responsible AI | April 2025 (Talk, Slides)
• LREC-COLING 2024 Tutorial: Hallucination in Large Language Models (Abstract, Proposal, Slides)
• AAAI 2025 Tutorial: Hallucination in Large Multimodal Models (Abstract, Slides)
• AAAI 2025 Tutorial: Neurosymbolic AI for EGI: Explainable, Grounded, and Instructable Generations (Abstract, Plan, Slides, Tutorial)

Publications

Text (NLP & LLMs)

• LLM Prompt Engineering, Training/Fine-tuning, & Alignment
• Retrieval-Augmented Generation (RAG)
• Hallucination Detection & Mitigation
• Bias & Fairness
• Knowledge Graphs & Graphical Models
• Synthetic Data Generation
• AI-Generated Text Detection
• Hate Speech & Content Moderation
• LLM Evaluation
• Indic LLMs

Vision (Image & Video AI)

• Text-to-Image Generation & Diffusion Models
• Image/Video Analysis & Understanding
• AI-Generated Image Detection
• Medical Image Processing
• Biometrics

Speech (Speech Recognition & Speaker Recognition)

• Speaker Verification & Recognition
• Automatic Speech Recognition (ASR)
• Keyword Spotting
• Representation Learning

Multimodal AI (Vision + Text)

• Vision-Language Models
• Multimodal Bias
• Representation Learning

Recommender Systems

Miscellaneous

Text (NLP & LLMs)


LLM Prompt Engineering, Training/Fine-tuning, & Alignment

LoRACode: LoRA Adapters for Code Embeddings

Gaussian Adaptive Attention is All You Need: Robust Contextual Representations Across Multiple Modalities (Media Coverage by Analytics India Magazine)

YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment

A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications (Citations: 500+)

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization

Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models

Parameter Efficient Fine Tuning (PEFT): A Comprehensive Analysis Across Applications

Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification

Dynamic Corrective Self-Distillation for Better Fine-Tuning of Pretrained Models

PHAnToM: Personality Has An Effect on Theory-of-Mind Reasoning in Large Language Models

Cause and Effect: Can Large Language Models Truly Understand Causality? (Citations: 5+)

The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey (Citations: 10+)

Retrieval-Augmented Generation (RAG)

SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval

Evidence-backed Fact Checking using Retrieval Augmented Generation and Few-Shot In-Context Learning with Large Language Models

Hallucination Detection & Mitigation

The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediations (Citations: 140+) (Media Coverage by The Washington Post)

Unveiling Hallucination in Text, Image, Video, and Audio Foundation Models: A Comprehensive Survey

A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models (Citations: 300+)

LREC-COLING 2024 Tutorial: Hallucination in Large Language Models

"Sorry, Come Again?" Prompting -- Enhancing Comprehension and Diminishing Hallucination with [PAUSE]-injected Optimal Paraphrasing

FACTOID: FACtual enTailment fOr hallucInation Detection

Bias & Fairness

Born With a Silver Spoon? Investigating Socioeconomic Bias in Large Language Models (Media Coverage by New Scientist; Article PDF)

COBIAS: Contextual Reliability in Bias Assessment

Unboxing Occupational Bias: Grounded Debiasing LLMs with U.S. Labor Data

From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings

Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems (Citations: 10+)

Knowledge Graphs & Graphical Models

ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs

RESTORE: Graph Embedding Assessment Through Reconstruction

Synthetic Data Generation

Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges (Citations: 10+)

Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering

AI-Generated Text Detection

Counter Turing Test (CT2): AI-Generated Text Detection is Not as Easy as You May Think - Introducing AI Detectability Index (ADI) (Citations: 15+) (Outstanding Paper Award)

A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization

Hate Speech & Content Moderation

Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement

Investigating Annotator Bias in Large Language Models for Hate Speech Detection

OffensiveLang: A Community Based Implicit Offensive Language Dataset

LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs

Causality Guided Disentanglement for Cross-Platform Hate Speech Detection

PEACE: Cross-Platform Hate Speech Detection -- A Causality-guided Framework (Citations: 20+)

LLM Evaluation

Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?

Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting

On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models

LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop (Citations: 5+)

AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach (Media Coverage by Analytics India Magazine)

ANALOGICAL -- A New Benchmark for Analogy of Long Text for Large Language Models (Citations: 20+)

Indic LLMs

IndicMMLU-Pro: Benchmarking the Indic Large Language Models

Multilingual State Space Models for Structured Question Answering in Indic Languages

Decoding the Diversity: A Review of the Indic AI Research Landscape

MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries (Citations: 5+) (Media Coverage by Analytics India Magazine)

CONFLATOR: Incorporating Switching Point based Rotatory Positional Encodings for Code-Mixed Language Modeling

Vision (Image & Video AI)


Text-to-Image Generation & Diffusion Models

Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation

Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation

Image/Video Analysis & Understanding

From Fog to Failure: How Dehazing Can Harm Clear Image Object Detection

ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models

Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers

iSeeBetter: Spatio-Temporal Video Super-Resolution using Recurrent Generative Back-Projection Networks (Citations: 30+)

Comparative Study and Optimization of Feature-Extraction Techniques for Content Based Image Retrieval (Citations: 120+)

AI-Generated Image Detection

Visual Counter Turing Test (VCT2): Discovering the Challenges for AI-Generated Image Detection and Introducing Visual AI Index (VAI)

The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks

Medical Image Processing

MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation

Biometrics

Face Recognition Using Discrete Cosine Transform for Global and Local Features (Citations: 80+)

Analysis of a Modern Voice Morphing Approach using Gaussian Mixture Models for Laryngectomees

A robust, low-cost approach to Face Detection and Face Recognition

Facial Expression Recognition using Squeeze and Excitation-powered Swin Transformers

Rotation, Scaling and Translation Analysis of Biometric Signature Templates

Speech (Speech Recognition & Speaker Recognition)


Speaker Verification & Recognition

Improving Speaker Verification Robustness With Synthetic Emotional Utterances

Post-training Embedding Alignment for Decoupling Enrollment and Runtime Speaker Recognition Models

Text-Independent Speaker Recognition for Low SNR Environments with Encryption

Keyword Spotting

I See What You Hear: A Vision-Inspired Method to Localize Words

Automatic Speech Recognition (ASR)

Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring

Representation Learning

DM-Codec: Distilling Multimodal Representations for Speech Tokenization

Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders

Audio Watermarking with Error Correction

Multimodal AI (Vision + Text)


Vision-Language Models

The Evolution of Multimodal Model Architectures

Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types

CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare (Citations: 15+)

FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering

FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering (Citations: 15+)

MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention

Enhancing Adverse Drug Event Detection with Multimodal Dataset: Corpus Creation and Model Development

On the Feasibility of Vision-Language Models for Time-Series Classification

Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions (Citations: 5+) (Top Ten List)

How Culturally Aware are Vision-Language Models? (Media Coverage by Analytics India Magazine)

Multimodal Bias

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages

Representation Learning

Cognitively Inspired Energy-Based World Models

IMAGINATOR: Pre-Trained Image+Text Joint Embeddings using Word-Level Grounding of Images

Few-shot Multimodal Multitask Multilingual Learning

iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability

iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering (Citations: 40+)

Recommender Systems

Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review (Citations: 10+)

Advancements in Modern Recommender Systems: Industrial Applications in Social Media, E-commerce, Entertainment, and Beyond

Miscellaneous

A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models

Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models (Citations: 15+)

The Evolution of Mixture of Experts: A Survey from Basics to Breakthroughs

RoundTable: Leveraging Dynamic Schema and Contextual Autocomplete for Enhanced Query Precision in Tabular Question Answering

SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection

Breaking Language Barriers: A Question Answering Dataset for Hindi and Marathi

Findings of Factify 2: Multimodal Fake News Detection (Citations: 10+)

Factify 2: A Multimodal Fake News and Satire News Dataset (Citations: 15+)

Overview of Memotion 3: Sentiment and Emotion Analysis of Codemixed Hinglish Memes

Memotion 3: Dataset on sentiment and emotion analysis of codemixed Hindi-English Memes

Design and Simulation of an 8-bit Dedicated Processor for calculating the Sine and Cosine of an Angle using CORDIC Algorithm

Dual-Layer Video Encryption using RSA Algorithm (Citations: 20+)

ARC Sort: Enhanced and Time Efficient Sorting Algorithm

Multi-Personality Partitioning for Heterogeneous Systems

Snow Avalanche: Study and Detection using Remote Sensing Techniques

Optimization Techniques for 160 GBPS WDM Optical Links to Minimize Nonlinear Effects

Performance Analysis of WDM-based Optical Communication Systems in presence of Kerr Nonlinearities

Compensation of Self Phase Modulation by Anomalous Dispersion in Nonlinear Optical Communication Systems