# Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models

arXiv: https://arxiv.org/abs/2311.07439 · HTML: https://mlsanity.com/paper/2311.07439/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 23 of 23)

- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (2019)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB](https://mlsanity.com/paper/1911.04944/) (2019)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs](https://mlsanity.com/paper/1911.06154/) (2019)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism](https://mlsanity.com/paper/1601.01073/) (2016)
- [Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation](https://mlsanity.com/paper/2105.08504/) (2021)
- [Zero-Resource Translation with Multi-Lingual Neural Machine Translation](https://mlsanity.com/paper/1606.04164/) (2016)
- [Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding](https://mlsanity.com/paper/2309.07098/) (2023)
- [Multi-Source Neural Translation](https://mlsanity.com/paper/1601.00710/) (2016)
- [Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages](https://mlsanity.com/paper/1909.09524/) (2019)
- [Neural Machine Translation with Pivot Languages](https://mlsanity.com/paper/1611.04928/) (2016)
- [SALTED: A Framework for SAlient Long-Tail Translation Error Detection](https://mlsanity.com/paper/2205.09988/) (2022)
- [What Do Compressed Multilingual Machine Translation Models Forget?](https://mlsanity.com/paper/2205.10828/) (2022)
- [Simultaneous Multi-Pivot Neural Machine Translation](https://mlsanity.com/paper/2104.07410/) (2021)
- [Robustness of Multi-Source MT to Transcription Errors](https://mlsanity.com/paper/2305.16894/) (2023)

## Built on by (most cited first, 5 of 5)

- [Revisiting Multilingual Data Mixtures in Language Model Pretraining](https://mlsanity.com/paper/2510.25947/) (2025)
- [EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation](https://mlsanity.com/paper/2403.00144/) (2024)
- [A Single Model Ensemble Framework for Neural Machine Translation using Pivot Translation](https://mlsanity.com/paper/2502.01182/) (2025)
- [In Data or Invisible: Toward a Better Digital Representation of Low-Resource Languages with Knowledge Graphs](https://mlsanity.com/paper/2605.05931/) (2026)
- [Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect Generation](https://mlsanity.com/paper/2609.04048/) (2026)

## Abstract (arXiv)

Massively multilingual machine translation models allow for the translation of a large number of languages with a single model, but have limited performance on low- and very-low-resource translation directions. Pivoting via high-resource languages remains a strong strategy for low-resource directions, and in this paper we revisit ways of pivoting through multiple languages. Previous work has used a simple averaging of probability distributions from multiple paths, but we find that this performs worse than using a single pivot, and exacerbates the hallucination problem because the same hallucinations can be probable across different paths. We also propose MaxEns, a novel combination strategy that makes the output biased towards the most confident predictions, hypothesising that confident predictions are less prone to be hallucinations. We evaluate different strategies on the FLORES benchmark for 20 low-resource language directions, demonstrating that MaxEns improves translation quality for low-resource languages while reducing hallucination in translations, compared to both direct translation and an averaging approach. On average, multi-pivot strategies still lag behind using English as a single pivot language, raising the question of how to identify the best pivoting strategy for a given translation direction.