123 citations · 147 across the 56 of their papers we have counts for
17 papers · 1 filter
AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
Aniruddha Roy, Jyoti Patel, Aman Chadha +2
Merging large language models (LLMs) is a practical way to compose capabilities from multiple fine-tuned checkpoints without retraining. Yet standard schemes (linear weight soups,…
D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space
Samarth Raina, Saksham Aggarwal, Aman Chadha +3
Preference-based post-training shapes language-model behavior, but safer outputs do not reveal how that change is represented internally or how firmly it persists under direct inte…
Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
Kartik Garg, Shourya Mishra, Kartikeya Sinha +8
Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving diff…
DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images
Dwip Dalal, Gautam Vashishtha, Anku Rani +11
The rise in harmful online content not only distorts public discourse but also poses significant challenges to maintaining a healthy digital environment. In response to this, we in…
nDNA -- the Semantic Helix of Artificial Cognition
Amitava Das
As AI foundation models grow in capability, a deeper question emerges: What shapes their internal cognitive identity -- beyond fluency and output? Benchmarks measure behavior, but…
A Comprehensive Dataset for Human vs. AI Generated Text Detection
Rajarshi Roy, Gurpreet Singh, Ashhar Aziz +17
The rapid advancement of large language models (LLMs) has led to increasingly human-like AI-generated text, raising concerns about content authenticity, misinformation, and trustwo…
AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
Snehasis Mukhopadhyay, Aryan Kasat, Shivam Dubey +5
Large Language Models (LLMs) can inadvertently reflect societal biases present in their training data, leading to harmful or prejudiced outputs. In the Indian context, our empirica…
AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
Amitava Das, Abhilekh Borah, Vinija Jain +1
Low-rank adaptation (LoRA) has become a standard tool for efficiently fine-tuning large language models (LLMs). Yet, even minor LoRA updates can induce alignment drift, weakening s…
TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
Amitava Das, Vinija Jain, Aman Chadha
Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial promp…
RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence
Vipula Rawte, Rajarshi Roy, Gurpreet Singh +11
As Large Language Models (LLMs) continue to advance, Retrieval-Augmented Generation (RAG) has emerged as a vital technique to enhance factual accuracy by integrating external knowl…
Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
Shreyas Dixit, Ashhar Aziz, Shashwat Bajpai +4
A report by the European Union Law Enforcement Agency predicts that by 2026, up to 90 percent of online content could be synthetically generated, raising concerns among policymaker…
QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization
Danush Khanna, Aditya Kumar Guru, Srivarshinee Sridhar +7
Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency h…
DETONATE: A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization
Renjith Prasad, Abhilekh Borah, Hasnat Md Abdullah +9
Alignment is crucial for text-to-image (T2I) models to ensure that generated images faithfully capture user intent while maintaining safety and fairness. Direct Preference Optimiza…
Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations
Abhilekh Borah, Chhavi Sharma, Danush Khanna +12
Alignment is no longer a luxury, it is a necessity. As large language models (LLMs) enter high-stakes domains like education, healthcare, governance, and law, their behavior must r…
AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
Danush Khanna, Gurucharan Marthi Krishna Kumar, Basab Ghosh +5
Adversarial threats against LLMs are escalating faster than current defenses can adapt. We expose a critical geometric blind spot in alignment: adversarial prompts exploit latent c…
YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment
Amitava Das, Yaswanth Narsupalli, Gurpreet Singh +5
Precise alignment in Text-to-Image (T2I) systems is crucial to ensure that generated visuals not only accurately encapsulate user intents but also conform to stringent ethical and…
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
Amitava Das, Suranjana Trivedy, Danush Khanna +8
The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Prefer…