Copertina

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models

Fuente: arXiv

Salvato in:

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

Documenti analoghi

SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
di: Das, Arion, 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)

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)

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)

Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
di: Saha, Anusa, 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)

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

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

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

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

The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey
di: Pawar, Saurav, et al.
Pubblicazione: (2024)

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

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

Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma
di: Sahoo, Subramanyam, 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)

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

AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
di: Mukhopadhyay, Snehasis, et al.
Pubblicazione: (2025)

Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
di: Sinha, Neelabh, 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)

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

SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection
di: Rani, Anku, et al.
Pubblicazione: (2023)

Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
di: Dixit, Shreyas, et al.
Pubblicazione: (2025)

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

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

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

SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation
di: Rawal, Niyati, et al.
Pubblicazione: (2026)

DeltaLogic: Minimal Premise Edits Reveal Belief-Revision Failures in Logical Reasoning Models
di: Dhanda, Amit
Pubblicazione: (2026)

Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
di: Kasat, Aryan, et al.
Pubblicazione: (2026)

Dial E for Ethical Enforcement: institutional VETO power as a governance primitive
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

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

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

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

Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
di: Vats, Arpita, et al.
Pubblicazione: (2024)

Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition
di: Joshi, Tanmay, et al.
Pubblicazione: (2026)

A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
di: Tonmoy, S. M Towhidul Islam, 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)

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

The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks
di: Barman, Niyar R, et al.
Pubblicazione: (2024)

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)