Cover Image

Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Tengyu, Duan, Zhichao, Li, Zhenyu, Dong, Bowen, Liu, Ning, Li, Xiuxing, Wang, Jianyong
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

COMM:Concentrated Margin Maximization for Robust Document-Level Relation Extraction
by: Duan, Zhichao, et al.
Published: (2025)

FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering
by: Li, Zhenyu, et al.
Published: (2023)

Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework
by: Li, Zhenyu, et al.
Published: (2022)

TROI: Cross-Subject Pretraining with Sparse Voxel Selection for Enhanced fMRI Visual Decoding
by: Wang, Ziyu, et al.
Published: (2025)

Efficient Attention Mechanisms for Large Language Models: A Survey
by: Sun, Yutao, et al.
Published: (2025)

Maximum Score Routing For Mixture-of-Experts
by: Dong, Bowen, et al.
Published: (2025)

FocusLLM: Precise Understanding of Long Context by Dynamic Condensing
by: Li, Zhenyu, et al.
Published: (2024)

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

Conan-embedding: General Text Embedding with More and Better Negative Samples
by: Li, Shiyu, et al.
Published: (2024)

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
by: Duan, Shitong, et al.
Published: (2024)

Semantic Adapter for Universal Text Embeddings: Diagnosing and Mitigating Negation Blindness to Enhance Universality
by: Cao, Hongliu
Published: (2025)

BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives
by: Sinha, Aarush, et al.
Published: (2025)

TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling
by: Liu, Longxiang, et al.
Published: (2024)

DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval
by: Lee, Taegyeong, et al.
Published: (2026)

Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification
by: Li, Zhijian, et al.
Published: (2024)

Enhancing Retrieval Performance: An Ensemble Approach For Hard Negative Mining
by: Meghwani, Hansa
Published: (2024)

Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding
by: Wang, Zijie, et al.
Published: (2026)

GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning
by: Solatorio, Aivin V.
Published: (2024)

Rethinking Negative Instances for Generative Named Entity Recognition
by: Ding, Yuyang, et al.
Published: (2024)

Learning Robust Negation Text Representations
by: Truong, Thinh Hung, et al.
Published: (2025)

When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
by: Zhang, Zhicheng, et al.
Published: (2026)

ReinPool: Reinforcement Learning Pooling Multi-Vector Embeddings for Retrieval System
by: Cha, Sungguk, et al.
Published: (2026)

AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives
by: Chen, Yanxi, et al.
Published: (2025)

ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining
by: Yu, Xiao, et al.
Published: (2025)

Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining
by: Le, Van-Hoang, et al.
Published: (2025)

Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization
by: Tian, Xueyun, et al.
Published: (2026)

Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples
by: Rösch, Philipp J., et al.
Published: (2024)

CATNIP: LLM Unlearning via Calibrated and Tokenized Negative Preference Alignment
by: Yang, Zhengbang, et al.
Published: (2026)

MGSA: Multi-Granularity Graph Structure Attention for Knowledge Graph-to-Text Generation
by: Wang, Shanshan, et al.
Published: (2024)

Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs
by: Thakur, Nandan, et al.
Published: (2025)

M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
by: Chen, Jianlv, et al.
Published: (2024)

Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking
by: Li, Zhuohao, et al.
Published: (2025)

AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings
by: Reddy, Revanth Gangi, et al.
Published: (2024)

NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli
by: Wang, Xu, et al.
Published: (2024)

Query-Aware Learnable Graph Pooling Tokens as Prompt for Large Language Models
by: Kim, Wooyoung, et al.
Published: (2025)

Negative-Prompt-driven Alignment for Generative Language Model
by: Qiao, Shiqi, et al.
Published: (2024)

Multi-Granularity Open Intent Classification via Adaptive Granular-Ball Decision Boundary
by: Li, Yanhua, et al.
Published: (2024)

The Impact of Negated Text on Hallucination with Large Language Models
by: Seo, Jaehyung, et al.
Published: (2025)

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
by: Park, Junsung, et al.
Published: (2025)

Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings
by: Hara, Tomomasa, et al.
Published: (2026)