Cover Image

Training LLMs to be Better Text Embedders through Bidirectional Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Su, Chang, Shi, Dengliang, Huang, Siyuan, Du, Jintao, Meng, Changhua, Cheng, Yu, Wang, Weiqiang, Lin, Zhouhan
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Gumbel Reranking: Differentiable End-to-End Reranker Optimization
by: Huang, Siyuan, et al.
Published: (2025)

A Multi-Task Embedder For Retrieval Augmented LLMs
by: Zhang, Peitian, et al.
Published: (2023)

Making Text Embedders Few-Shot Learners
by: Li, Chaofan, et al.
Published: (2024)

Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training
by: Su, Chang, et al.
Published: (2024)

LLM-based Embedders for Prior Case Retrieval
by: Premasiri, Damith, et al.
Published: (2025)

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
by: Sorokin, Artyom, et al.
Published: (2025)

Towards Cross-Modal Text-Molecule Retrieval with Better Modality Alignment
by: Song, Jia, et al.
Published: (2024)

VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation
by: Kim, Junyoung, et al.
Published: (2026)

Mirror-Consistency: Harnessing Inconsistency in Majority Voting
by: Huang, Siyuan, et al.
Published: (2024)

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model
by: Ju, Yeong-Joon, et al.
Published: (2025)

Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
by: Dai, Yuqin, et al.
Published: (2025)

Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information
by: Long, Kehan, et al.
Published: (2025)

Text Clustering as Classification with LLMs
by: Huang, Chen, et al.
Published: (2024)

Topic-Specific Classifiers are Better Relevance Judges than Prompted LLMs
by: Gienapp, Lukas, et al.
Published: (2025)

Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
by: Lin, Huifeng, et al.
Published: (2025)

Bert4XMR: Cross-Market Recommendation with Bidirectional Encoder Representations from Transformer
by: Hu, Zheng, et al.
Published: (2023)

Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning
by: Li, Jinzheng, et al.
Published: (2025)

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
by: Tan, Jiejun, et al.
Published: (2024)

LLMs as Better Recommenders with Natural Language Collaborative Signals: A Self-Assessing Retrieval Approach
by: Xin, Haoran, et al.
Published: (2025)

Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG
by: Zhong, Jiarui, et al.
Published: (2026)

Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights
by: Wu, Yifan, et al.
Published: (2025)

Study on LLMs for Promptagator-Style Dense Retriever Training
by: Gwon, Daniel, et al.
Published: (2025)

RREH: Reconstruction Relations Embedded Hashing for Semi-Paired Cross-Modal Retrieval
by: Wang, Jianzong, et al.
Published: (2024)

Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL
by: Nahid, Md Mahadi Hasan, et al.
Published: (2025)

Improving Sequential Recommendations via Bidirectional Temporal Data Augmentation with Pre-training
by: Jiang, Juyong, et al.
Published: (2021)

Unifying Adversarial Robustness and Training Across Text Scoring Models
by: Tamber, Manveer Singh, et al.
Published: (2026)

A Survey on Deep Text Hashing: Efficient Semantic Text Retrieval with Binary Representation
by: He, Liyang, et al.
Published: (2025)

Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
by: Liang, Jintao, et al.
Published: (2025)

Post-Training Denoising of User Profiles with LLMs in Collaborative Filtering Recommendation
by: Dervishaj, Ervin, et al.
Published: (2026)

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
by: Zhang, Wenlin, et al.
Published: (2025)

Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers
by: Huang, Wei, et al.
Published: (2026)

Towards Better Understanding of User Satisfaction in Open-Domain Conversational Search
by: Chu, Zhumin, et al.
Published: (2022)

Efficient Multi-task Prompt Tuning for Recommendation
by: Bai, Ting, et al.
Published: (2024)

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models
by: Zhao, Shilong, et al.
Published: (2025)

FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training
by: Li, Yuyuan, et al.
Published: (2025)

Behavior Modeling Space Reconstruction for E-Commerce Search
by: Wang, Yejing, et al.
Published: (2025)

Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretation
by: Zhong, Yunfei, et al.
Published: (2025)

Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs
by: Cattaneo, Alberto, et al.
Published: (2025)

Towards a Barrier-free GeoQA Portal: Natural Language Interaction with Geospatial Data Using Multi-Agent LLMs and Semantic Search
by: Feng, Yu, et al.
Published: (2025)

Towards Better Search with Domain-Aware Text Embeddings for C2C Marketplaces
by: Rusli, Andre, et al.
Published: (2025)