hard-negative

#hard-negative

Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Text-to-Image Retrieval

arXiv cs.AI ↗ · yesterday Cached

This paper compares natively multimodal embedding models (Gemini Embedding 2, Amazon Nova 2) against frontier LLMs (GPT-4.1, Claude Sonnet 4.6) for hard-negative text-to-image retrieval, finding comparable accuracy but much lower latency for embedding-based ranking.

0 favorites 0 likes

#hard-negative

ECI_{sem}: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives

Hugging Face Daily Papers ↗ · 2026-06-05 Cached

ECI_sem is a training-free method for ranking hard negative sources in dense retrieval using frozen embeddings, achieving strong performance on MS MARCO and BEIR benchmarks.

0 favorites 0 likes

hard-negative

Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Text-to-Image Retrieval

ECI_{sem}: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives

Submit Feedback