Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data

arXiv:2604.17738 · cs.CL, cs.LG · Submitted 2026-04-20 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-04-20

Updated: 2026-04-20

Terminology

• Embeddings — 3× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• LoRA Adaptation — 1× in this paper · explained in 2 episodes

Sources

• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• LoRA: Low-Rank Adaptation of Large Language Models
• InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval
• Towards General Text Embeddings with Multi-stage Contrastive Learning
• Passage Re-ranking with BERT
• RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!
• jina-embeddings-v3: Multilingual Embeddings With Task LoRA
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• C-Pack: Packed Resources For General Chinese Embeddings

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering