Cover Image

Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rohweder, Jonas, Dutta, Subhabrata, Gurevych, Iryna
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Patches of Nonlinearity: Instruction Vectors in Large Language Models
by: Bigoulaeva, Irina, et al.
Published: (2026)

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling
by: Tamoyan, Hovhannes, et al.
Published: (2025)

Expert Preference-based Evaluation of Automated Related Work Generation
by: Şahinuç, Furkan, et al.
Published: (2025)

Reward Modeling for Scientific Writing Evaluation
by: Şahinuç, Furkan, et al.
Published: (2026)

SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling
by: Rizvi, Md Imbesat Hassan, et al.
Published: (2025)

Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
by: Niu, Jingcheng, et al.
Published: (2025)

Differentially Private Steering for Large Language Model Alignment
by: Goel, Anmol, et al.
Published: (2025)

How Quantization Shapes Bias in Large Language Models
by: Marcuzzi, Federico, et al.
Published: (2025)

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models
by: Rizvi, Md Imbesat Hassan, et al.
Published: (2024)

Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
by: Sahnan, Dhruv, et al.
Published: (2026)

How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning
by: Dutta, Subhabrata, et al.
Published: (2024)

Uncertainty-Aware Decoding with Minimum Bayes Risk
by: Daheim, Nico, et al.
Published: (2025)

ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links
by: Basch, Serwar, et al.
Published: (2025)

Towards Automated Error Discovery: A Study in Conversational AI
by: Petrak, Dominic, et al.
Published: (2025)

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
by: Geng, Jiahui, et al.
Published: (2025)

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
by: Daheim, Nico, et al.
Published: (2024)

Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure
by: Maheshwari, Gaurav, et al.
Published: (2024)

MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
by: Macina, Jakub, et al.
Published: (2025)

Model Merging by Uncertainty-Based Gradient Matching
by: Daheim, Nico, et al.
Published: (2023)

Mechanistic Behavior Editing of Language Models
by: Singh, Joykirat, et al.
Published: (2024)

Localized LoRA: A Structured Low-Rank Approximation for Efficient Fine-Tuning
by: Barazandeh, Babak, et al.
Published: (2025)

Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction
by: Goh, Hui Wen, et al.
Published: (2026)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
by: Geiping, Jonas, et al.
Published: (2025)

Discovering Semantic Latent Structures in Psychological Scales: A Response-Free Pathway to Efficient Simplification
by: Wang, Bo, et al.
Published: (2026)

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models
by: Dawes, Cutter, et al.
Published: (2026)

Unifying Linear-Time Attention via Latent Probabilistic Modelling
by: Dolga, Rares, et al.
Published: (2024)

Unified Scaling Laws for Compressed Representations
by: Panferov, Andrei, et al.
Published: (2025)

Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
by: Qin, Tian, et al.
Published: (2024)

FUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing
by: Liu, Chen Cecilia, et al.
Published: (2023)

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
by: Guo, Phillip, et al.
Published: (2024)

Unifying Learning Dynamics and Generalization in Transformers Scaling Law
by: Yang, Chiwun
Published: (2025)

Compression Scaling Laws:Unifying Sparsity and Quantization
by: Frantar, Elias, et al.
Published: (2025)

Efficient Alignment of Large Language Models via Data Sampling
by: Khera, Amrit, et al.
Published: (2024)

Early Period of Training Impacts Adaptation for Out-of-Distribution Generalization: An Empirical Study
by: Liu, Chen Cecilia, et al.
Published: (2024)

Subjective Code Preferences in Experts and Large Language Models
by: Mokhova, Anna, et al.
Published: (2026)

HIPPD: Brain-Inspired Hierarchical Information Processing for Personality Detection
by: Chen, Guanming, et al.
Published: (2025)

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior
by: Huang, Zeyi, et al.
Published: (2026)

Is Peer Review Really in Decline? Analyzing Review Quality across Venues and Time
by: Kuznetsov, Ilia, et al.
Published: (2026)

Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework
by: Dycke, Nils, et al.
Published: (2025)

Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification
by: Bates, Luke, et al.
Published: (2023)