# BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models

arXiv: https://arxiv.org/abs/2306.10968 · HTML: https://mlsanity.com/paper/2306.10968/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 19 Jun 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [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)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback](https://mlsanity.com/paper/2304.02426/) (2023)
- [Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model](https://mlsanity.com/paper/2011.11499/) (2020)
- [End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages](https://mlsanity.com/paper/2106.12398/) (2021)

## Built on by (most cited first, 30 of 42)

- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models](https://mlsanity.com/paper/2309.11674/) (2023)
- [Extrapolating Large Language Models to Non-English by Aligning Languages](https://mlsanity.com/paper/2308.04948/) (2023)
- [Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations](https://mlsanity.com/paper/2310.20246/) (2023)
- [TIM: Teaching Large Language Models to Translate with Comparison](https://mlsanity.com/paper/2307.04408/) (2023)
- [(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts](https://mlsanity.com/paper/2405.11804/) (2024)
- [Radiology-Llama2: Best-in-Class Large Language Model for Radiology](https://mlsanity.com/paper/2309.06419/) (2023)
- [X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale](https://mlsanity.com/paper/2410.03115/) (2024)
- [Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations](https://mlsanity.com/paper/2308.14186/) (2023)
- [SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection](https://mlsanity.com/paper/2402.16705/) (2024)
- [Aligning Large Language Models with Human: A Survey](https://mlsanity.com/paper/2307.12966/) (2023)
- [Improving Translation Faithfulness of Large Language Models via Augmenting Instructions](https://mlsanity.com/paper/2308.12674/) (2023)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data](https://mlsanity.com/paper/2310.05242/) (2023)
- [TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning](https://mlsanity.com/paper/2404.19597/) (2024)
- [Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions](https://mlsanity.com/paper/2401.08088/) (2024)
- [Evaluating Large Language Models for Radiology Natural Language Processing](https://mlsanity.com/paper/2307.13693/) (2023)
- [Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study](https://mlsanity.com/paper/2412.18260/) (2024)
- [Instruction Position Matters in Sequence Generation with Large Language Models](https://mlsanity.com/paper/2308.12097/) (2023)
- [Improving Machine Translation with Large Language Models: A Preliminary Study with Cooperative Decoding](https://mlsanity.com/paper/2311.02851/) (2023)
- [Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models](https://mlsanity.com/paper/2406.16135/) (2024)
- [BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment](https://mlsanity.com/paper/2411.16300/) (2024)
- [Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation](https://mlsanity.com/paper/2503.06594/) (2025)
- [The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights](https://mlsanity.com/paper/2405.01345/) (2024)
- [Unified Segment-to-Segment Framework for Simultaneous Sequence Generation](https://mlsanity.com/paper/2310.17940/) (2023)
- [How Multilingual Are Large Language Models Fine-Tuned for Translation?](https://mlsanity.com/paper/2405.20512/) (2024)
- [Lens: Rethinking Multilingual Enhancement for Large Language Models](https://mlsanity.com/paper/2410.04407/) (2024)
- [Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation](https://mlsanity.com/paper/2410.13944/) (2024)
- [Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints](https://mlsanity.com/paper/2409.14469/) (2024)
- [DEPT: Decoupled Embeddings for Pre-training Language Models](https://mlsanity.com/paper/2410.05021/) (2024)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable prowess in language understanding and generation. Advancing from foundation LLMs to instructionfollowing LLMs, instruction tuning plays a vital role in aligning LLMs to human preferences. However, the existing LLMs are usually focused on English, leading to inferior performance in non-English languages. In order to improve the performance for non-English languages, it is necessary to collect language-specific training data for foundation LLMs and construct language-specific instructions for instruction tuning, both of which are heavy loads. To minimize human workload, we propose to transfer the capabilities of language generation and instruction following from English to other languages through an interactive translation task. We have developed BayLing, an instruction-following LLM by utilizing LLaMA as the foundation LLM and automatically constructing interactive translation instructions for instructing tuning. Extensive assessments demonstrate that BayLing achieves comparable performance to GPT-3.5-turbo, despite utilizing a considerably smaller parameter size of only 13 billion. Experimental results on translation tasks show that BayLing achieves 95% of single-turn translation capability compared to GPT-4 with automatic evaluation and 96% of interactive translation capability compared to GPT-3.5-turbo with human evaluation. To estimate the performance on general tasks, we created a multi-turn instruction test set called BayLing-80. The experimental results on BayLing-80 indicate that BayLing achieves 89% of performance compared to GPT-3.5-turbo. BayLing also demonstrates outstanding performance on knowledge assessment of Chinese GaoKao and English SAT, second only to GPT-3.5-turbo among a multitude of instruction-following LLMs. Demo, homepage, code and models of BayLing are available.