Cover Image

Behavior-Equivalent Token: Single-Token Replacement for Long Prompts in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dong, Jiancheng, Jia, Pengyue, Peng, Jingyu, Wang, Maolin, Wang, Yuhao, Su, Lixin, Sun, Xin, Wang, Shuaiqiang, Yin, Dawei, Zhao, Xiangyu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How to Utilize Complementary Vision-Text Information for 2D Structure Understanding
by: Dong, Jiancheng, et al.
Published: (2026)

MOSAIC: Composable Safety Alignment with Modular Control Tokens
by: Peng, Jingyu, et al.
Published: (2026)

AdaSwitch: Balancing Exploration and Guidance in Knowledge Distillation via Adaptive Switching
by: Peng, Jingyu, et al.
Published: (2025)

Stepwise Reasoning Error Disruption Attack of LLMs
by: Peng, Jingyu, et al.
Published: (2024)

MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
by: Jia, Pengyue, et al.
Published: (2023)

G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
by: Jia, Pengyue, et al.
Published: (2024)

DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent
by: Wu, Tongzhou, et al.
Published: (2026)

Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
by: Peng, Jingyu, et al.
Published: (2025)

Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models
by: Wang, Yuhao, et al.
Published: (2024)

Joint Semantic Token Selection and Prompt Optimization for Interpretable Prompt Learning
by: Wang, Yating, et al.
Published: (2026)

AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
by: Li, Qiyang, et al.
Published: (2026)

Can LLM Annotations Replace User Clicks for Learning to Rank?
by: Yu, Lulu, et al.
Published: (2025)

CoRanking: Collaborative Ranking with Small and Large Ranking Agents
by: Liu, Wenhan, et al.
Published: (2025)

LongAttn: Selecting Long-context Training Data via Token-level Attention
by: Wu, Longyun, et al.
Published: (2025)

Cross-model Control: Improving Multiple Large Language Models in One-time Training
by: Wu, Jiayi, et al.
Published: (2024)

TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection
by: Zhou, Qihang, et al.
Published: (2025)

XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies
by: Ni, Xuanfan, et al.
Published: (2024)

TAPO: Task-Referenced Adaptation for Prompt Optimization
by: Luo, Wenxin, et al.
Published: (2025)

Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs
by: Pan, Wenbo, et al.
Published: (2026)

Tokenize Anything via Prompting
by: Pan, Ting, et al.
Published: (2023)

From Prompting to Alignment: A Generative Framework for Query Recommendation
by: Min, Erxue, et al.
Published: (2025)

TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning
by: Ni, Hang, et al.
Published: (2025)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
by: Wu, Wei, et al.
Published: (2024)

Large Language Model Enhanced Recommender Systems: A Survey
by: Liu, Qidong, et al.
Published: (2024)

Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification
by: Zhang, Pingping, et al.
Published: (2024)

VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
by: Ren, Xubin, et al.
Published: (2025)

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
by: Gao, Heyang, et al.
Published: (2025)

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
by: Song, Yuhan, et al.
Published: (2025)

Empowering Denoising Sequential Recommendation with Large Language Model Embeddings
by: Wu, Tongzhou, et al.
Published: (2025)

MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning
by: Wang, Maolin, et al.
Published: (2025)

LLMs + Persona-Plug = Personalized LLMs
by: Liu, Jiongnan, et al.
Published: (2024)

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
by: Tian, Han, et al.
Published: (2026)

PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks
by: Ge, Qingqing, et al.
Published: (2023)

SIGMA: Selective Gated Mamba for Sequential Recommendation
by: Liu, Ziwei, et al.
Published: (2024)

MTA: A Merge-then-Adapt Framework for Personalized Large Language Model
by: Li, Xiaopeng, et al.
Published: (2025)

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
by: Chai, Ziwei, et al.
Published: (2024)

AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning
by: Bai, Jisheng, et al.
Published: (2023)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
by: Geng, Runpeng, et al.
Published: (2025)

Towards Next-Generation Recommender Systems: A Benchmark for Personalized Recommendation Assistant with LLMs
by: Huang, Jiani, et al.
Published: (2025)

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation
by: Jia, Pengyue, et al.
Published: (2024)