# Do Multilingual Encoders Produce Language-Consistent Semantic IDs?

arXiv: https://arxiv.org/abs/2610.01139 · HTML: https://mlsanity.com/paper/2610.01139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 8 of 8)

- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search](https://mlsanity.com/paper/2206.06588/) (2022)
- [Cross-Market Product Recommendation](https://mlsanity.com/paper/2109.05929/) (2021)
- [Multilingual Generative Retrieval via Cross-lingual Semantic Compression](https://mlsanity.com/paper/2510.07812/) (2025)
- [Decoupled Residual Quantization for Robust Semantic IDs in Recommendation](https://mlsanity.com/paper/2606.01844/) (2026)

## Abstract (arXiv)

Semantic IDs (SIDs) compress item embeddings into discrete code sequences used in generative retrieval. We ask whether a multilingual encoder is sufficient for different-language renderings of the same product to receive language-consistent SIDs. Using Amazon ESCI listings rendered in English, Spanish, and Japanese, we test whether translations remain close to their English source, whether residual quantization is unusually sensitive to translation-induced movement, and whether multilingual or language-balanced quantizer fitting improves SID agreement. Multilingual E5 places translations measurably apart: under an English-heavy fit, a Japanese translation preserves the first SID code of its English counterpart in only 7.7% of cases, compared with 89.0% for an English rewording. Distance-matched product-directed controls produce nearly the same full-SID mismatch as translation, providing no evidence that the quantizer selectively amplifies language directions. Balancing the fitting mixture makes codebook use more uniform but further reduces cross-lingual prefix agreement: Spanish first-code consistency falls from 28.3% to 6.6%, while an English-only fit preserves it for 67.6% of Spanish translations. These results show that multilingual exposure and balanced codebook use alone do not guarantee language-consistent SIDs.