Imagen de Portada

Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nguyen, Trung, Leng, Yan
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Offline Preference Optimization via Maximum Marginal Likelihood Estimation
por: Najafi, Saeed, et al.
Publicado: (2025)

The Linear Representation Hypothesis and the Geometry of Large Language Models
por: Park, Kiho, et al.
Publicado: (2023)

Lizard: An Efficient Linearization Framework for Large Language Models
por: Van Nguyen, Chien, et al.
Publicado: (2025)

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models
por: Bello, Femi, et al.
Publicado: (2025)

Structured Pruning for Diverse Best-of-N Reasoning Optimization
por: Nguyen, Hieu Trung, et al.
Publicado: (2025)

Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation
por: Vargas, Francisco, et al.
Publicado: (2020)

Task-driven Layerwise Additive Activation Intervention
por: Nguyen, Hieu Trung, et al.
Publicado: (2025)

Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons
por: Leng, Yongqi, et al.
Publicado: (2024)

How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
por: Garg, Nikhil, et al.
Publicado: (2026)

Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
por: Man, Hieu, et al.
Publicado: (2026)

Optimizing Multi-Stage Language Models for Effective Text Retrieval
por: Trung, Quang Hoang, et al.
Publicado: (2024)

On the Origins of Linear Representations in Large Language Models
por: Jiang, Yibo, et al.
Publicado: (2024)

Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation
por: Rozzio, Adam, et al.
Publicado: (2026)

Large Language Model-Enhanced Algorithm Selection: Towards Comprehensive Algorithm Representation
por: Wu, Xingyu, et al.
Publicado: (2023)

Don't Read Everything: A Curvature-Conditioned Query for Linear Attention
por: Le, Dong, et al.
Publicado: (2026)

Towards Generalising Neural Topical Representations
por: Yang, Xiaohao, et al.
Publicado: (2023)

Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimation
por: Akyildiz, Ö. Deniz, et al.
Publicado: (2023)

NoveltyRank: A Retrieval-Augmented Framework for Conceptual Novelty Estimation in AI Research
por: Yan, Zhengxu, et al.
Publicado: (2025)

SEA: Sparse Linear Attention with Estimated Attention Mask
por: Lee, Heejun, et al.
Publicado: (2023)

HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation
por: Liu, Haokun, et al.
Publicado: (2025)

Large Language Models Encode Semantics and Alignment in Linearly Separable Representations
por: Saglam, Baturay, et al.
Publicado: (2025)

Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval
por: Trung, Quang Hoang, et al.
Publicado: (2024)

MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment
por: Hong, Dang Nguyen, et al.
Publicado: (2026)

Reasoning Planning for Language Models
por: Nguyen, Bao, et al.
Publicado: (2025)

Mixture-of-Personas Language Models for Population Simulation
por: Bui, Ngoc, et al.
Publicado: (2025)

Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation
por: Phan, Buu, et al.
Publicado: (2025)

Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
por: Xie, Wanyun, et al.
Publicado: (2025)

VITRO: Vocabulary Inversion for Time-series Representation Optimization
por: Bellos, Filippos, et al.
Publicado: (2024)

Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
por: Nguyen, Hieu Trung, et al.
Publicado: (2026)

Towards Efficient Active Learning in NLP via Pretrained Representations
por: Vysogorets, Artem, et al.
Publicado: (2024)

Maximum Score Routing For Mixture-of-Experts
por: Dong, Bowen, et al.
Publicado: (2025)

Failure Modes of Maximum Entropy RLHF
por: Çağatan, Ömer Veysel, et al.
Publicado: (2025)

Scientific Hypothesis Generation and Validation: Methods, Datasets, and Future Directions
por: Kulkarni, Adithya, et al.
Publicado: (2025)

ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods
por: Xie, Roy, et al.
Publicado: (2024)

Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior
por: Gong, Yue, et al.
Publicado: (2025)

Learning State-Tracking from Code Using Linear RNNs
por: Siems, Julien, et al.
Publicado: (2026)

Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective
por: Zeng, Shenglai, et al.
Publicado: (2024)

Disentangling the Roles of Representation and Selection in Data Pruning
por: Du, Yupei, et al.
Publicado: (2025)

What Do Language Models Learn in Context? The Structured Task Hypothesis
por: Li, Jiaoda, et al.
Publicado: (2024)

Neural Attention Search Linear: Towards Adaptive Token-Level Hybrid Attention Models
por: Deng, Difan, et al.
Publicado: (2026)