Copertina

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jin, Mingyu, Yu, Qinkai, Huang, Jingyuan, Zeng, Qingcheng, Wang, Zhenting, Hua, Wenyue, Zhao, Haiyan, Mei, Kai, Meng, Yanda, Ding, Kaize, Yang, Fan, Du, Mengnan, Zhang, Yongfeng
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Impact of Reasoning Step Length on Large Language Models
di: Jin, Mingyu, et al.
Pubblicazione: (2024)

Health-LLM: Personalized Retrieval-Augmented Disease Prediction System
di: Yu, Qinkai, et al.
Pubblicazione: (2024)

Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
di: Zeng, Qingcheng, et al.
Pubblicazione: (2024)

Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities
di: Tang, Hua, et al.
Pubblicazione: (2024)

Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis
di: Li, Daoyang, et al.
Pubblicazione: (2024)

What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents
di: Xue, Zhaoqian, et al.
Pubblicazione: (2024)

Fact or Facsimile? Evaluating the Factual Robustness of Modern Retrievers
di: Wu, Haoyu, et al.
Pubblicazione: (2025)

EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
di: Lin, Sam, et al.
Pubblicazione: (2024)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
di: Zhao, Haiyan, et al.
Pubblicazione: (2024)

ADO: Automatic Data Optimization for Inputs in LLM Prompts
di: Lin, Sam, et al.
Pubblicazione: (2025)

Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
di: Jin, Mingyu, et al.
Pubblicazione: (2025)

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
di: Zhao, Haiyan, et al.
Pubblicazione: (2025)

ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction
di: Jin, Mingyu, et al.
Pubblicazione: (2024)

Knowledge Graph Large Language Model (KG-LLM) for Link Prediction
di: Shu, Dong, et al.
Pubblicazione: (2024)

When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
di: Zhang, Chong, et al.
Pubblicazione: (2024)

From Commands to Prompts: LLM-based Semantic File System for AIOS
di: Shi, Zeru, et al.
Pubblicazione: (2024)

Data-centric NLP Backdoor Defense from the Lens of Memorization
di: Wang, Zhenting, et al.
Pubblicazione: (2024)

OpenP5: An Open-Source Platform for Developing, Training, and Evaluating LLM-based Recommender Systems
di: Xu, Shuyuan, et al.
Pubblicazione: (2023)

Toward Equitable Access: Leveraging Crowdsourced Reviews to Investigate Public Perceptions of Health Resource Accessibility
di: Xue, Zhaoqian, et al.
Pubblicazione: (2025)

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
di: Henry, James
Pubblicazione: (2026)

GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models
di: Rivera, Oscar, et al.
Pubblicazione: (2026)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
di: Zhang, Hanrong, et al.
Pubblicazione: (2024)

MoralBench: Moral Evaluation of LLMs
di: Ji, Jianchao, et al.
Pubblicazione: (2024)

DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
di: Guo, Minghao, et al.
Pubblicazione: (2025)

SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
di: He, Zirui, et al.
Pubblicazione: (2025)

Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation
di: Shi, Kaize, et al.
Pubblicazione: (2024)

AIOS: LLM Agent Operating System
di: Mei, Kai, et al.
Pubblicazione: (2024)

RAPTOR: Ridge-Adaptive Logistic Probes
di: Gao, Ziqi, et al.
Pubblicazione: (2026)

TrustAgent: Towards Safe and Trustworthy LLM-based Agents
di: Hua, Wenyue, et al.
Pubblicazione: (2024)

Towards Uncovering How Large Language Model Works: An Explainability Perspective
di: Zhao, Haiyan, et al.
Pubblicazione: (2024)

Concept-Centric Token Interpretation for Vector-Quantized Generative Models
di: Yang, Tianze, et al.
Pubblicazione: (2025)

War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
di: Hua, Wenyue, et al.
Pubblicazione: (2023)

Separable Multi-Concept Erasure from Diffusion Models
di: Zhao, Mengnan, et al.
Pubblicazione: (2024)

Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer
di: Han, Wenkang, et al.
Pubblicazione: (2025)

Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
di: Jin, Mingyu, et al.
Pubblicazione: (2026)

A Novel Robotic Variable Stiffness Mechanism Based on Helically Wound Structured Electrostatic Layer Jamming
di: Bai, Congrui, et al.
Pubblicazione: (2025)

PAP-REC: Personalized Automatic Prompt for Recommendation Language Model
di: Li, Zelong, et al.
Pubblicazione: (2024)

NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes
di: Fan, Lizhou, et al.
Pubblicazione: (2023)

UP5: Unbiased Foundation Model for Fairness-aware Recommendation
di: Hua, Wenyue, et al.
Pubblicazione: (2023)

Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
di: Li, Zelong, et al.
Pubblicazione: (2024)