Image de couverture de livre

Training Superior Sparse Autoencoders for Instruct Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Jiaming, Ye, Haoran, Chen, Yukun, Li, Xinyue, Zhang, Lei, Alinejad-Rokny, Hamid, Peng, Jimmy Chih-Hsien, Yang, Min
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare
par: Zhu, Jingwei, et autres
Publié: (2024)

Small Language Model as Data Prospector for Large Language Model
par: Ni, Shiwen, et autres
Publié: (2024)

InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?
par: Wang, Qiyao, et autres
Publié: (2026)

RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
par: Chen, Yukun, et autres
Publié: (2026)

STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation
par: Li, Jiaming, et autres
Publié: (2025)

PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination
par: Wang, Qiyao, et autres
Publié: (2026)

Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
par: Li, Shuaimin, et autres
Publié: (2025)

Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
par: Chen, Dingwei, et autres
Publié: (2025)

PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data Augmentation
par: Luo, Jing, et autres
Publié: (2024)

FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
par: Wang, Qiyao, et autres
Publié: (2026)

Lower Layers Matter: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused
par: Chen, Dingwei, et autres
Publié: (2024)

PLOT: Enhancing Preference Learning via Optimal Transport
par: Zhu, Liang, et autres
Publié: (2026)

ToolRM: Towards Agentic Tool-Use Reward Modeling
par: Li, Renhao, et autres
Publié: (2025)

EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
par: Xu, Ancheng, et autres
Publié: (2025)

Time-Aware Feature Selection: Adaptive Temporal Masking for Stable Sparse Autoencoder Training
par: Li, T. Ed, et autres
Publié: (2025)

Model Unlearning via Sparse Autoencoder Subspace Guided Projections
par: Wang, Xu, et autres
Publié: (2025)

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis
par: Luo, Run, et autres
Publié: (2025)

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
par: Li, Jiaming, et autres
Publié: (2025)

Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
par: Jing, Yi, et autres
Publié: (2026)

CLaSp: In-Context Layer Skip for Self-Speculative Decoding
par: Chen, Longze, et autres
Publié: (2025)

Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
par: Li, Xiaochuan, et autres
Publié: (2024)

AlignSAE: Concept-Aligned Sparse Autoencoders
par: Yang, Minglai, et autres
Publié: (2025)

xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
par: Lee, Sunbowen, et autres
Publié: (2025)

ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance
par: Shamsi, Afshar, et autres
Publié: (2024)

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
par: Zheng, Carolina, et autres
Publié: (2025)

InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
par: Wei, Zhepei, et autres
Publié: (2024)

Sparse Autoencoder Features for Classifications and Transferability
par: Gallifant, Jack, et autres
Publié: (2025)

AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents
par: Chen, Guhong, et autres
Publié: (2024)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
par: Li, Aaron J., et autres
Publié: (2025)

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity
par: Fang, Feiteng, et autres
Publié: (2025)

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
par: O'Neill, Charles, et autres
Publié: (2024)

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
par: Karvonen, Adam, et autres
Publié: (2025)

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
par: Yamashita, Tomoya, et autres
Publié: (2025)

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders
par: Yu, Zhuohao, et autres
Publié: (2025)

EdgeInfinite-Instruct: Bridging SFT-Based Optimization and NPU-Level Efficiency for Edge Devices
par: Chen, Jiyu, et autres
Publié: (2025)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
par: Wang, Xu, et autres
Publié: (2026)

InstructPro: Natural Language Guided Ligand-Binding Protein Design
par: Song, Zhenqiao, et autres
Publié: (2025)

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
par: Koromilas, Panagiotis, et autres
Publié: (2026)

Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder
par: Yang, Xianjun, et autres
Publié: (2025)

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks
par: Karvonen, Adam, et autres
Publié: (2024)