Copertina

Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Ningyu, Zhang, Qi, Qiu, Xipeng, Huang, Xuanjing
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe
di: Xu, Ningyu, et al.
Pubblicazione: (2024)

Revealing emergent human-like conceptual representations from language prediction
di: Xu, Ningyu, et al.
Pubblicazione: (2025)

Emergent Hierarchical Structure in Large Language Models: An Information-Theoretic Framework for Multi-Scale Representation
di: Zhang, Yukin, et al.
Pubblicazione: (2025)

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
di: Wang, Siyin, et al.
Pubblicazione: (2024)

AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems
di: Wang, Weiyi, et al.
Pubblicazione: (2026)

Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning
di: Zhao, Jun, et al.
Pubblicazione: (2024)

Uncovering Emergent Physics Representations Learned In-Context by Large Language Models
di: Song, Yeongwoo, et al.
Pubblicazione: (2025)

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
di: Yang, Yukang, et al.
Pubblicazione: (2025)

Evaluating the Performance of Large Language Models on GAOKAO Benchmark
di: Zhang, Xiaotian, et al.
Pubblicazione: (2023)

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
di: Zhao, Jun, et al.
Pubblicazione: (2024)

Are Large Language Models Good Prompt Optimizers?
di: Ma, Ruotian, et al.
Pubblicazione: (2024)

Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective
di: Li, Tianlong, et al.
Pubblicazione: (2024)

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
di: Zhang, Hanzhi, et al.
Pubblicazione: (2025)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
di: Xi, Zhiheng, et al.
Pubblicazione: (2023)

Navigating the OverKill in Large Language Models
di: Shi, Chenyu, et al.
Pubblicazione: (2024)

Context Structure Reshapes the Representational Geometry of Language Models
di: Hosseini, Eghbal A., et al.
Pubblicazione: (2026)

Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
di: Li, Ming, et al.
Pubblicazione: (2023)

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
di: He, Wei, et al.
Pubblicazione: (2024)

XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
di: Dong, Yixin, et al.
Pubblicazione: (2024)

AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
di: Xi, Zhiheng, et al.
Pubblicazione: (2024)

ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages
di: Ye, Junjie, et al.
Pubblicazione: (2024)

Struct-X: Enhancing Large Language Models Reasoning with Structured Data
di: Tan, Xiaoyu, et al.
Pubblicazione: (2024)

E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
di: Li, Yun, et al.
Pubblicazione: (2023)

Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
di: Ye, Junjie, et al.
Pubblicazione: (2025)

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning
di: Ye, Junjie, et al.
Pubblicazione: (2024)

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
di: Lv, Huijie, et al.
Pubblicazione: (2024)

Emergent Introspective Awareness in Large Language Models
di: Lindsey, Jack
Pubblicazione: (2026)

LLaMA Beyond English: An Empirical Study on Language Capability Transfer
di: Zhao, Jun, et al.
Pubblicazione: (2024)

Understanding the Dilemma of Unlearning for Large Language Models
di: Zhang, Qingjie, et al.
Pubblicazione: (2025)

ContextGuard: Structured Self-Auditing for Context Learning in Language Models
di: Jin, Hongbo, et al.
Pubblicazione: (2026)

Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges
di: Xu, Weilun, et al.
Pubblicazione: (2026)

Identifying Semantic Induction Heads to Understand In-Context Learning
di: Ren, Jie, et al.
Pubblicazione: (2024)

LongSafety: Enhance Safety for Long-Context LLMs
di: Huang, Mianqiu, et al.
Pubblicazione: (2024)

Evolution of Concepts in Language Model Pre-Training
di: Ge, Xuyang, et al.
Pubblicazione: (2025)

Balanced Data Sampling for Language Model Training with Clustering
di: Shao, Yunfan, et al.
Pubblicazione: (2024)

GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation
di: Zong, Yi, et al.
Pubblicazione: (2024)

BiasEdit: Debiasing Stereotyped Language Models via Model Editing
di: Xu, Xin, et al.
Pubblicazione: (2025)

LongHeads: Multi-Head Attention is Secretly a Long Context Processor
di: Lu, Yi, et al.
Pubblicazione: (2024)

Do Large Language Models Understand Logic or Just Mimick Context?
di: Yan, Junbing, et al.
Pubblicazione: (2024)

KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion
di: Wei, Yanbin, et al.
Pubblicazione: (2024)