# NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance

arXiv: https://arxiv.org/abs/2507.09601 · HTML: https://mlsanity.com/paper/2507.09601/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 13 Jul 2025.

## Builds on (most cited first, 12 of 12)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain](https://mlsanity.com/paper/2211.00083/) (2022)
- [TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning](https://mlsanity.com/paper/2104.06979/) (2021)
- [FinMTEB: Finance Massive Text Embedding Benchmark](https://mlsanity.com/paper/2502.10990/) (2025)
- [Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial Narratives](https://mlsanity.com/paper/2403.14341/) (2024)
- [TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts](https://mlsanity.com/paper/2502.07131/) (2025)
- [Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation](https://mlsanity.com/paper/2503.09094/) (2025)

## Built on by (most cited first, 1 of 1)

- [AI PB: A Grounded Generative Agent for Personalized Investment Insights](https://mlsanity.com/paper/2510.20099/) (2025)

## Abstract (arXiv)

Financial text embeddings must distinguish changes in event status, perspective, and obligations even when passages share similar wording. NMIXX adapts existing encoders through 18.8k source-linked triplets: paraphrases and Korean-English translations preserve meaning, while targeted financial rewrites introduce semantic contrasts. We examine this recipe across seven backbones on English and Korean financial and general-domain semantic textual similarity (STS), and analyze the composition and passage lengths of KorFinSTS. BGE-M3 attains the highest adapted financial correlations in this comparison, improving from 0.1969 to 0.2967 on FinSTS and from 0.0512 to 0.2732 on KorFinSTS. Its general English and Korean correlations decrease by 0.0391 and 0.0463. Across the seven models, five improve their mean financial correlation, but all reduce their mean general-domain correlation. Per-language comparisons and benchmark-weight sensitivity analysis reveal differences obscured by a single aggregate score. The study contributes a finance-specific supervision design and evidence for evaluating adaptation jointly with retained general semantic capability; direct cross-language retrieval remains outside its evaluation scope.