Cover Image

TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Das, Amitava, Jain, Vinija, Chadha, Aman
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
by: Das, Arion, et al.
Published: (2026)

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

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

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

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

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

Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
by: Garg, Kartik, et al.
Published: (2025)

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

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

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

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

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

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

Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation
by: Lakhanpal, Sanyam, et al.
Published: (2024)

On the Feasibility of Vision-Language Models for Time-Series Classification
by: Prithyani, Vinay, et al.
Published: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models
by: Rawte, Vipula, et al.
Published: (2024)

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

MOD-X: A Modular Open Decentralized eXchange Framework proposal for Heterogeneous Interoperable Artificial Intelligence Agents
by: Ioannides, Georgios, et al.
Published: (2025)

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

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

Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles
by: Budagam, Devichand, et al.
Published: (2024)

From Fog to Failure: The Unintended Consequences of Dehazing on Object Detection in Clear Images
by: Kumar, Ashutosh, et al.
Published: (2025)