Cover Image

Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Anhao, Ye, Fanghua, Fu, Jinlan, Shen, Xiaoyu
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding
by: Tong, Junlong, et al.
Published: (2025)

SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling
by: Zhao, Anhao, et al.
Published: (2025)

$\mathcal{V}isi\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs
by: Fan, Yingqi, et al.
Published: (2025)

StreamingThinker: Large Language Models Can Think While Reading
by: Tong, Junlong, et al.
Published: (2025)

Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
by: Zhao, Anhao, et al.
Published: (2026)

From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models
by: Ding, Longwei, et al.
Published: (2026)

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
by: Xiong, Jing, et al.
Published: (2025)

MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation
by: Fu, Jinlan, et al.
Published: (2025)

Unveiling LLMs' Metaphorical Understanding: Exploring Conceptual Irrelevance, Context Leveraging and Syntactic Influence
by: Ye, Fengying, et al.
Published: (2025)

Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
by: Chen, Xinghao, et al.
Published: (2025)

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
by: Fu, Jinlan, et al.
Published: (2025)

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
by: Chen, Qian, et al.
Published: (2026)

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
by: Zhang, Haowei, et al.
Published: (2026)

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
by: Liu, Wenjie, et al.
Published: (2026)

CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations
by: Xu, Lin, et al.
Published: (2024)

A Global Context Mechanism for Sequence Labeling
by: Xu, Conglei, et al.
Published: (2023)

Conversation Kernels: A Flexible Mechanism to Learn Relevant Context for Online Conversation Understanding
by: Agarwal, Vibhor, et al.
Published: (2025)

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
by: Zhang, Weixu, et al.
Published: (2026)

Understanding In-Context Learning from Repetitions
by: Yan, Jianhao, et al.
Published: (2023)

Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment
by: Pei, Jiahuan, et al.
Published: (2025)

Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning
by: Wang, Xiao, et al.
Published: (2024)

LLM can Achieve Self-Regulation via Hyperparameter Aware Generation
by: Wang, Siyin, et al.
Published: (2024)

The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis
by: Zhang, Miaoran, et al.
Published: (2024)

How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation
by: Xiao, Yang, et al.
Published: (2023)

Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge
by: Fu, Jinlan, et al.
Published: (2024)

Chain of Thought Explanation for Dialogue State Tracking
by: Xu, Lin, et al.
Published: (2024)

Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant
by: Shen, Lei, et al.
Published: (2025)

A Survey to Recent Progress Towards Understanding In-Context Learning
by: Mao, Haitao, et al.
Published: (2024)

What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
by: Fan, Yingqi, et al.
Published: (2026)

Understanding Synthetic Context Extension via Retrieval Heads
by: Zhao, Xinyu, et al.
Published: (2024)

Deconstructing In-Context Learning: Understanding Prompts via Corruption
by: Shivagunde, Namrata, et al.
Published: (2024)

The Few Govern the Many:Unveiling Few-Layer Dominance for Time Series Models
by: Qiu, Xin, et al.
Published: (2025)

UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation
by: Li, Zixuan, et al.
Published: (2024)

CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
by: Liu, Cheng, et al.
Published: (2025)

An ERP Study of Recursive Possessive Parsing in ASD Children and Its Cognitive Neuro Mechanisms
by: Chenxi, Fu, et al.
Published: (2026)

FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understanding
by: Deng, Jingyang, et al.
Published: (2024)

Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning
by: Doan, Nhi Hoai, et al.
Published: (2025)

Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation
by: Wang, Yuhao, et al.
Published: (2025)

Beyond English: Unveiling Multilingual Bias in LLM Copyright Compliance
by: Chen, Yupeng, et al.
Published: (2025)

Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
by: Chen, Xinghao, et al.
Published: (2025)