# Plug, Play, and Fuse: Zero-Shot Joint Decoding via Word-Level Re-ranking Across Diverse Vocabularies

arXiv: https://arxiv.org/abs/2408.11327 · HTML: https://mlsanity.com/paper/2408.11327/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 62 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 30 of 36)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Multi30K: Multilingual English-German Image Descriptions](https://mlsanity.com/paper/1605.00459/) (2016)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [SaulLM-7B: A pioneering Large Language Model for Law](https://mlsanity.com/paper/2403.03883/) (2024)
- [Learning Compact Metrics for MT](https://mlsanity.com/paper/2110.06341/) (2021)
- [Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2309.11925/) (2023)
- [Learning to Decode Collaboratively with Multiple Language Models](https://mlsanity.com/paper/2403.03870/) (2024)
- [Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus](https://mlsanity.com/paper/2006.05754/) (2020)
- [Bridging the Gap between Different Vocabularies for LLM Ensemble](https://mlsanity.com/paper/2404.09492/) (2024)
- [Ensemble Distillation for Neural Machine Translation](https://mlsanity.com/paper/1702.01802/) (2017)
- [Mutual Information and Diverse Decoding Improve Neural Machine Translation](https://mlsanity.com/paper/1601.00372/) (2016)
- [Simple Fusion: Return of the Language Model](https://mlsanity.com/paper/1809.00125/) (2018)
- [Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation](https://mlsanity.com/paper/2212.10140/) (2022)

## Abstract (arXiv)

Recent advancements in NLP have resulted in models with specialized strengths, such as processing multimodal inputs or excelling in specific domains. However, real-world tasks, like multimodal translation, often require a combination of these strengths, such as handling both translation and image processing. While individual translation and vision models are powerful, they typically lack the ability to perform both tasks in a single system. Combining these models poses challenges, particularly due to differences in their vocabularies, which limit the effectiveness of traditional ensemble methods to post-generation techniques like N-best list re-ranking. In this work, we propose a novel zero-shot ensembling strategy that allows for the integration of different models during the decoding phase without the need for additional training. Our approach re-ranks beams during decoding by combining scores at the word level, using heuristics to predict when a word is completed. We demonstrate the effectiveness of this method in machine translation scenarios, showing that it enables the generation of translations that are both speech- and image-aware while also improving overall translation quality (We will release the code upon paper acceptance.).