arXiv Machine Learning June 2, 2026 By Zhicheng Zhang, Jiwei Tang, Kuicai Dong, Xiaopeng Li, Jieming Zhu, Jingyu Li, Qianhui Zhu, Fengyuan Lu, Wang Jiaheng, Gang Wang, Hai-Tao Zheng, Zhaocheng Du

When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval

Read the original on arXiv Machine Learning →

arXiv:2606. 01304v1 Announce Type: new Abstract: Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriever score rather than diagnostic value, and increasingly contaminated by false positives as the retriever improves.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Jun 8

$\mathrm{ECI}_{\mathrm{sem}}$: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives

arXiv:2603. 20990v3 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation.

By Aarush Sinha, Rahul Seetharaman, Aman Bansal

llms rag nlp fine-tuning safety

arXiv AI

Aug 5

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model

arXiv:2508. 00955v3 Announce Type: replace-cross Abstract: Adapting generative Multimodal Large Language Models (MLLMs) into universal embedding models typically demands resource-intensive contrastive pre-training, while traditional hard negative mining methods suffer from severe false negative contamination.

By Yeong-Joon Ju, Seong-Whan Lee

llms rag fine-tuning multimodal benchmarks

arXiv AI

Jun 6

ECI: Effective Contrastive Information to Evaluate Hard-Negatives

arXiv:2603. 20990v2 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation.

By Aarush Sinha, Rahul Seetharaman, Aman Bansal

llms rag nlp fine-tuning safety

arXiv AI

6d ago

Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement

arXiv:2605. 05103v3 Announce Type: replace-cross Abstract: We introduce the \textbf{Concept Field} of a text corpus: a local drift field with pointwise uncertainty, estimated in sentence-embedding space from the deltas between consecutive sentences.

By Nicholas S. Kersting, Vittorio Castelli, Chieh Ting Yeh, Xinzhu Wang, Saad Taame, Khaoula Allak

llms rag safety

arXiv AI

Jun 11

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

arXiv:2603. 22934v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack surface.

By Xiangyu Yin, Yi Qi, Chih-Hong Cheng

llms rag

arXiv AI

Jun 19

ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval

arXiv:2606. 20280v1 Announce Type: cross Abstract: Leveraging Multimodal Large Language Models (MLLMs) via contrastive learning has become a mainstream paradigm for improving the performance of Universal Multimodal Retrieval (UMR).

By Yuhan Liu, Pei Fu, Hang Li, Yukun Qi, Chao Jiang, Jingwen Fu, Zhen Liu, Bin Qin, Zhenbo Luo, Jian Luan, Jingmin Xin

llms reinforcement-learning multimodal benchmarks

Related stories

$\mathrm{ECI}_{\mathrm{sem}}$: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives

From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model

ECI: Effective Contrastive Information to Evaluate Hard-Negatives

Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval