Imagen de Portada

Learn Your Reference Model for Real Good Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gorbatovski, Alexey, Shaposhnikov, Boris, Malakhov, Alexey, Surnachev, Nikita, Aksenov, Yaroslav, Maksimov, Ian, Balagansky, Nikita, Gavrilov, Daniil
Formato:	Preprint
Publicado:	2024
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

Linear Transformers with Learnable Kernel Functions are Better In-Context Models
por: Aksenov, Yaroslav, et al.
Publicado: (2024)

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models
por: Laptev, Daniil, et al.
Publicado: (2025)

Trust-Region Behavior Blending for On-Policy Distillation
por: Plyusov, Daniil, et al.
Publicado: (2026)

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
por: Kurochkin, Vadim, et al.
Publicado: (2025)

The Differences Between Direct Alignment Algorithms are a Blur
por: Gorbatovski, Alexey, et al.
Publicado: (2025)

Teach Old SAEs New Domain Tricks with Boosting
por: Koriagin, Nikita, et al.
Publicado: (2025)

You Do Not Fully Utilize Transformer's Representation Capacity
por: Gerasimov, Gleb, et al.
Publicado: (2025)

Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
por: Sinii, Viacheslav, et al.
Publicado: (2025)

ESSA: Evolutionary Strategies for Scalable Alignment
por: Korotyshova, Daria, et al.
Publicado: (2025)

Steering LLM Reasoning Through Bias-Only Adaptation
por: Sinii, Viacheslav, et al.
Publicado: (2025)

F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
por: Plyusov, Daniil, et al.
Publicado: (2026)

Mechanistic Permutability: Match Features Across Layers
por: Balagansky, Nikita, et al.
Publicado: (2024)

Diffusion Language Models Generation Can Be Halted Early
por: Vaina, Sofia Maria Lo Cicero, et al.
Publicado: (2023)

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy
por: Balagansky, Nikita, et al.
Publicado: (2025)

Next Embedding Prediction Makes World Models Stronger
por: Bredis, George, et al.
Publicado: (2026)

Learning Shortest Paths with Generative Flow Networks
por: Morozov, Nikita, et al.
Publicado: (2026)

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning
por: Rukhovich, Alexey, et al.
Publicado: (2025)

Revisiting Non-Acyclic GFlowNets in Discrete Environments
por: Morozov, Nikita, et al.
Publicado: (2025)

Reinforcement learning for question answering in programming domain using public community scoring as a human feedback
por: Gorbatovski, Alexey, et al.
Publicado: (2024)

Guided Star-Shaped Masked Diffusion
por: Meshchaninov, Viacheslav, et al.
Publicado: (2025)

When an LLM is apprehensive about its answers -- and when its uncertainty is justified
por: Sychev, Petr, et al.
Publicado: (2025)

Complexity-aware fine-tuning
por: Goncharov, Andrey, et al.
Publicado: (2025)

Developing Lightweight DNN Models With Limited Data For Real-Time Sign Language Recognition
por: Nikitin, Nikita, et al.
Publicado: (2025)

Generative Flow Networks as Entropy-Regularized RL
por: Tiapkin, Daniil, et al.
Publicado: (2023)

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
por: Sedykh, Ivan, et al.
Publicado: (2026)

Review, Remask, Refine (R3): Process-Guided Block Diffusion for Text Generation
por: Mounier, Nikita, et al.
Publicado: (2025)

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
por: Kachaev, Nikita, et al.
Publicado: (2025)

On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
por: Fan, Dongyang, et al.
Publicado: (2024)

Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting
por: Proskura, Polina, et al.
Publicado: (2024)

VARAN: Variational Inference for Self-Supervised Speech Models Fine-Tuning on Downstream Tasks
por: Diatlova, Daria, et al.
Publicado: (2025)

Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation
por: Sorokin, Nikita, et al.
Publicado: (2026)

Scalable Parameter-Light Spectral Method for Clustering Short Text Embeddings with a Cohesion-Based Evaluation Metric
por: Neveditsin, Nikita, et al.
Publicado: (2025)

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows
por: Borovkov, Nikita, et al.
Publicado: (2026)

Pairwise Reference Alignment as a Model-Level Ordinal Observable
por: Li, Mujing
Publicado: (2026)

L3Cube-MahaSum: A Comprehensive Dataset and BART Models for Abstractive Text Summarization in Marathi
por: Deshmukh, Pranita, et al.
Publicado: (2024)

SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?
por: Lu, Xudong, et al.
Publicado: (2025)

Language steering in latent space to mitigate unintended code-switching
por: Goncharov, Andrey, et al.
Publicado: (2025)

Improving GFlowNets with Monte Carlo Tree Search
por: Morozov, Nikita, et al.
Publicado: (2024)

SLaNC: Static LayerNorm Calibration
por: Salmani, Mahsa, et al.
Publicado: (2024)

Large Human Language Models: A Need and the Challenges
por: Soni, Nikita, et al.
Publicado: (2023)