Image de couverture de livre

AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mukhopadhyay, Snehasis, Kasat, Aryan, Dubey, Shivam, Karthikeyan, Rahul, Sood, Dhruv, Jain, Vinija, Chadha, Aman, Das, Amitava
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
par: Kasat, Aryan, et autres
Publié: (2026)

TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
par: Das, Amitava, et autres
Publié: (2025)

AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
par: Das, Amitava, et autres
Publié: (2025)

ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
par: Wanaskar, Kapil, et autres
Publié: (2026)

AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
par: Roy, Aniruddha, et autres
Publié: (2025)

D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space
par: Raina, Samarth, et autres
Publié: (2025)

SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
par: Das, Arion, et autres
Publié: (2026)

Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
par: Saha, Anusa, et autres
Publié: (2026)

Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
par: Sinha, Neelabh, et autres
Publié: (2024)

PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
par: Kumar, Harsh, et autres
Publié: (2026)

LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs
par: Sidibomma, Rushendra, et autres
Publié: (2024)

MAAT: Multi-phase Adapter-Aware Targeted Unlearning
par: Yagnik, Suryash, et autres
Publié: (2026)

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
par: Saha, Partha Pratim, et autres
Publié: (2026)

Born With a Silver Spoon? Investigating Socioeconomic Bias in Large Language Models
par: Singh, Smriti, et autres
Publié: (2024)

Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma
par: Sahoo, Subramanyam, et autres
Publié: (2025)

DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents
par: Mukhopadhyay, Snehasis
Publié: (2026)

Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
par: Vats, Arpita, et autres
Publié: (2024)

KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
par: Wijesiriwardene, Thilini, et autres
Publié: (2024)

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
par: Sahoo, Subramanyam, et autres
Publié: (2026)

YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment
par: Das, Amitava, et autres
Publié: (2025)

Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
par: Sinha, Neelabh, et autres
Publié: (2024)

I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift
par: Sahoo, Subramanyam, et autres
Publié: (2026)

Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
par: Dixit, Shreyas, et autres
Publié: (2025)

Decoding the Diversity: A Review of the Indic AI Research Landscape
par: KJ, Sankalp, et autres
Publié: (2024)

Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation
par: Kumar, Tanay, et autres
Publié: (2026)

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
par: Chauhan, Anay, et autres
Publié: (2026)

Multilingual State Space Models for Structured Question Answering in Indic Languages
par: Vats, Arpita, et autres
Publié: (2025)

On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models
par: Wijesiriwardene, Thilini, et autres
Publié: (2023)

The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey
par: Pawar, Saurav, et autres
Publié: (2024)

SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation
par: Rawal, Niyati, et autres
Publié: (2026)

Assessing LLM Reliability on Temporally Recent Open-Domain Questions
par: Krishnappa, Pushwitha, et autres
Publié: (2026)

SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection
par: Rani, Anku, et autres
Publié: (2023)

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
par: Sahoo, Subramanyam, et autres
Publié: (2026)

Dial E for Ethical Enforcement: institutional VETO power as a governance primitive
par: Sahoo, Subramanyam, et autres
Publié: (2026)

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
par: Sahoo, Subramanyam, et autres
Publié: (2026)

SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval
par: Mahalingam, Aakash, et autres
Publié: (2024)

Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
par: Aggarwal, Yash, et autres
Publié: (2026)

A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
par: Tonmoy, S. M Towhidul Islam, et autres
Publié: (2024)

The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks
par: Barman, Niyar R, et autres
Publié: (2024)

How Culturally Aware are Vision-Language Models?
par: Burda-Lassen, Olena, et autres
Publié: (2024)