Copertina

SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Das, Arion, Saha, Partha Pratim, Dhanda, Amit, Jain, Vinija, Chadha, Aman, Das, Amitava
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
di: Saha, Partha Pratim, et al.
Pubblicazione: (2026)

AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
di: Das, Amitava, et al.
Pubblicazione: (2025)

ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
di: Wanaskar, Kapil, et al.
Pubblicazione: (2026)

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
di: Chauhan, Anay, et al.
Pubblicazione: (2026)

Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
di: Saha, Anusa, et al.
Pubblicazione: (2026)

TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
di: Das, Amitava, et al.
Pubblicazione: (2025)

PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
di: Kumar, Harsh, et al.
Pubblicazione: (2026)

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

Overview of Factify5WQA: Fact Verification through 5W Question-Answering
di: Suresh, Suryavardan, et al.
Pubblicazione: (2024)

Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
di: Sinha, Neelabh, et al.
Pubblicazione: (2024)

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
di: Sinha, Neelabh, et al.
Pubblicazione: (2024)

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

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
di: Das, Amitava, et al.
Pubblicazione: (2025)

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

Decoding the Diversity: A Review of the Indic AI Research Landscape
di: KJ, Sankalp, et al.
Pubblicazione: (2024)

Assessing LLM Reliability on Temporally Recent Open-Domain Questions
di: Krishnappa, Pushwitha, et al.
Pubblicazione: (2026)

AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
di: Roy, Aniruddha, et al.
Pubblicazione: (2025)

On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models
di: Wijesiriwardene, Thilini, et al.
Pubblicazione: (2023)

MAAT: Multi-phase Adapter-Aware Targeted Unlearning
di: Yagnik, Suryash, et al.
Pubblicazione: (2026)

CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation
di: Sinha, Aarush, et al.
Pubblicazione: (2026)

Evaluating Negative Sampling Approaches for Neural Topic Models
di: Adhya, Suman, et al.
Pubblicazione: (2025)

Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications
di: Balne, Charith Chandra Sai, et al.
Pubblicazione: (2024)

KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
di: Wijesiriwardene, Thilini, et al.
Pubblicazione: (2024)

How Culturally Aware are Vision-Language Models?
di: Burda-Lassen, Olena, et al.
Pubblicazione: (2024)

A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models
di: Sahoo, Pranab, et al.
Pubblicazione: (2024)

YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment
di: Das, Amitava, et al.
Pubblicazione: (2025)

Investigating Annotator Bias in Large Language Models for Hate Speech Detection
di: Das, Amit, et al.
Pubblicazione: (2024)

nDNA -- the Semantic Helix of Artificial Cognition
di: Das, Amitava
Pubblicazione: (2025)

AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
di: Khanna, Danush, et al.
Pubblicazione: (2025)

I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations
di: Borah, Abhilekh, et al.
Pubblicazione: (2025)

Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs
di: Singhal, Ronit, et al.
Pubblicazione: (2024)

Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
di: Ghosh, Akash, et al.
Pubblicazione: (2024)

Born With a Silver Spoon? Investigating Socioeconomic Bias in Large Language Models
di: Singh, Smriti, et al.
Pubblicazione: (2024)

A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models
di: Khoshnoodi, Mahsa, et al.
Pubblicazione: (2024)

Multilingual State Space Models for Structured Question Answering in Indic Languages
di: Vats, Arpita, et al.
Pubblicazione: (2025)

Can Large Language Models Infer Causal Relationships from Real-World Text?
di: Saklad, Ryan, et al.
Pubblicazione: (2025)

Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2025)

A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
di: Sahoo, Pranab, et al.
Pubblicazione: (2024)