Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fu, Yuchen, Cheng, Zifeng, Jiang, Zhiwei, Wang, Zhonghui, Yin, Yafeng, Li, Zhengliang, Gu, Qing
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
par: Cheng, Zifeng, et autres
Publié: (2025)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
par: Cheng, Zifeng, et autres
Publié: (2025)

GenEOL: Harnessing the Generative Power of LLMs for Training-Free Sentence Embeddings
par: Thirukovalluru, Raghuveer, et autres
Publié: (2024)

RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection
par: Yang, Shufan, et autres
Publié: (2025)

Multi-Prompting Decoder Helps Better Language Understanding
par: Cheng, Zifeng, et autres
Publié: (2024)

Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
par: Wang, Cong, et autres
Publié: (2025)

Eliciting Better Multilingual Structured Reasoning from LLMs through Code
par: Li, Bryan, et autres
Publié: (2024)

Computer Environments Elicit General Agentic Intelligence in LLMs
par: Cheng, Daixuan, et autres
Publié: (2026)

Verbal Process Supervision Elicits Better Coding Agents
par: Chen, Hao-Yuan, et autres
Publié: (2025)

Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings
par: Sastre, Ignacio, et autres
Publié: (2025)

Executable Code Actions Elicit Better LLM Agents
par: Wang, Xingyao, et autres
Publié: (2024)

LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings
par: Philippy, Fred, et autres
Publié: (2024)

Logic-Regularized Verifier Elicits Reasoning from LLMs
par: Wang, Xinyu, et autres
Publié: (2026)

AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
par: Gu, Zhouhong, et autres
Publié: (2024)

Latent Reasoning via Sentence Embedding Prediction
par: Hwang, Hyeonbin, et autres
Publié: (2025)

Training LLMs Beyond Next Token Prediction -- Filling the Mutual Information Gap
par: Yang, Chun-Hao, et autres
Publié: (2025)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
par: Deiseroth, Björn, et autres
Publié: (2024)

AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
par: Qing, Liu, et autres
Publié: (2026)

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
par: Sung, Yi-Lin, et autres
Publié: (2025)

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
par: Bi, Baolong, et autres
Publié: (2024)

LeDex: Training LLMs to Better Self-Debug and Explain Code
par: Jiang, Nan, et autres
Publié: (2024)

Static Word Embeddings for Sentence Semantic Representation
par: Wada, Takashi, et autres
Publié: (2025)

Predicting Oscar-Nominated Screenplays with Sentence Embeddings
par: Gross, Francis
Publié: (2025)

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
par: Li, Yan, et autres
Publié: (2025)

Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings
par: Oh, Minsik, et autres
Publié: (2023)

TNCSE: Tensor's Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings
par: Zong, Tianyu, et autres
Publié: (2025)

Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs
par: Nimmagadda, Satya Sri Rajiteswari, et autres
Publié: (2026)

Unsupervised Candidate Ranking for Lexical Substitution via Holistic Sentence Semantics
par: Hu, Zhongyang, et autres
Publié: (2025)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
par: Han, Pengrui, et autres
Publié: (2026)

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
par: Zhang, Yunxiang, et autres
Publié: (2025)

SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features
par: Opitz, Juri, et autres
Publié: (2022)

HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives
par: Liu, Wenxiao, et autres
Publié: (2024)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
par: Liu, Jingyu, et autres
Publié: (2025)

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
par: Li, Jindong, et autres
Publié: (2025)

Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
par: Lin, Ailiang, et autres
Publié: (2025)

Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
par: Si, Jianfeng, et autres
Publié: (2025)

Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter
par: Chen, Junhao, et autres
Publié: (2024)

Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
par: Ning, Xuefei, et autres
Publié: (2024)

Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
par: Goddard, Charles, et autres
Publié: (2025)

Better Embeddings with Coupled Adam
par: Stollenwerk, Felix, et autres
Publié: (2025)