Cover Image

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Yuchen, Cheng, Zifeng, Jiang, Zhiwei, Wang, Zhonghui, Yin, Yafeng, Li, Zhengliang, Gu, Qing
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
by: Cheng, Zifeng, et al.
Published: (2025)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
by: Cheng, Zifeng, et al.
Published: (2025)

GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings
by: Thirukovalluru, Raghuveer, et al.
Published: (2024)

RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection
by: Yang, Shufan, et al.
Published: (2025)

Multi-Prompting Decoder Helps Better Language Understanding
by: Cheng, Zifeng, et al.
Published: (2024)

Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
by: Wang, Cong, et al.
Published: (2025)

Eliciting Better Multilingual Structured Reasoning from LLMs through Code
by: Li, Bryan, et al.
Published: (2024)

Computer Environments Elicit General Agentic Intelligence in LLMs
by: Cheng, Daixuan, et al.
Published: (2026)

Verbal Process Supervision Elicits Better Coding Agents
by: Chen, Hao-Yuan, et al.
Published: (2025)

Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings
by: Sastre, Ignacio, et al.
Published: (2025)

Executable Code Actions Elicit Better LLM Agents
by: Wang, Xingyao, et al.
Published: (2024)

LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings
by: Philippy, Fred, et al.
Published: (2024)

Logic-Regularized Verifier Elicits Reasoning from LLMs
by: Wang, Xinyu, et al.
Published: (2026)

AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
by: Gu, Zhouhong, et al.
Published: (2024)

Latent Reasoning via Sentence Embedding Prediction
by: Hwang, Hyeonbin, et al.
Published: (2025)

Training LLMs Beyond Next Token Prediction -- Filling the Mutual Information Gap
by: Yang, Chun-Hao, et al.
Published: (2025)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
by: Deiseroth, Björn, et al.
Published: (2024)

AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
by: Qing, Liu, et al.
Published: (2026)

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
by: Sung, Yi-Lin, et al.
Published: (2025)

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
by: Bi, Baolong, et al.
Published: (2024)

LeDex: Training LLMs to Better Self-Debug and Explain Code
by: Jiang, Nan, et al.
Published: (2024)

Static Word Embeddings for Sentence Semantic Representation
by: Wada, Takashi, et al.
Published: (2025)

Predicting Oscar-Nominated Screenplays with Sentence Embeddings
by: Gross, Francis
Published: (2025)

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
by: Li, Yan, et al.
Published: (2025)

Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings
by: Oh, Minsik, et al.
Published: (2023)

TNCSE: Tensor's Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings
by: Zong, Tianyu, et al.
Published: (2025)

Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs
by: Nimmagadda, Satya Sri Rajiteswari, et al.
Published: (2026)

Unsupervised Candidate Ranking for Lexical Substitution via Holistic Sentence Semantics
by: Hu, Zhongyang, et al.
Published: (2025)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
by: Zhang, Yunxiang, et al.
Published: (2025)

SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features
by: Opitz, Juri, et al.
Published: (2022)

HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives
by: Liu, Wenxiao, et al.
Published: (2024)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
by: Liu, Jingyu, et al.
Published: (2025)

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
by: Li, Jindong, et al.
Published: (2025)

Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
by: Lin, Ailiang, et al.
Published: (2025)

Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
by: Si, Jianfeng, et al.
Published: (2025)

Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter
by: Chen, Junhao, et al.
Published: (2024)

Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
by: Ning, Xuefei, et al.
Published: (2024)

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
by: Goddard, Charles, et al.
Published: (2025)

Better Embeddings with Coupled Adam
by: Stollenwerk, Felix, et al.
Published: (2025)