# SimulPL: Aligning Human Preferences in Simultaneous Machine Translation

arXiv: https://arxiv.org/abs/2502.00634 · HTML: https://mlsanity.com/paper/2502.00634/

## Key facts

- Cited by 7 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 32 of its 52 references that are in the map.
- First posted on arXiv 2 Feb 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Disentangling Length from Quality in Direct Preference Optimization](https://mlsanity.com/paper/2403.19159/) (2024)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016)
- [SimulEval: An Evaluation Toolkit for Simultaneous Translation](https://mlsanity.com/paper/2007.16193/) (2020)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [Can neural machine translation do simultaneous translation?](https://mlsanity.com/paper/1606.02012/) (2016)
- [Preference Transformer: Modeling Human Preferences using Transformers for RL](https://mlsanity.com/paper/2303.00957/) (2023)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translation](https://mlsanity.com/paper/2206.05807/) (2022)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model](https://mlsanity.com/paper/2401.12873/) (2024)
- [Hidden Markov Transformer for Simultaneous Machine Translation](https://mlsanity.com/paper/2303.00257/) (2023)
- [Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings](https://mlsanity.com/paper/2010.11247/) (2020)
- [Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution](https://mlsanity.com/paper/2402.11525/) (2024)
- [LiveMind: Low-latency Large Language Models with Simultaneous Inference](https://mlsanity.com/paper/2406.14319/) (2024)
- [Simultaneous Machine Translation with Large Language Models](https://mlsanity.com/paper/2309.06706/) (2023)
- [Simultaneous Machine Translation with Tailored Reference](https://mlsanity.com/paper/2310.13588/) (2023)
- [Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models](https://mlsanity.com/paper/2312.04691/) (2023)

## Built on by (most cited first, 7 of 7)

- [SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation](https://mlsanity.com/paper/2505.20622/) (2025)
- [Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice](https://mlsanity.com/paper/2507.17527/) (2025)
- [InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model](https://mlsanity.com/paper/2503.02969/) (2025)
- [PRIM: Towards Practical In-Image Multilingual Machine Translation](https://mlsanity.com/paper/2509.05146/) (2025)
- [Simultaneous Speech-to-Speech Translation Without Aligned Data](https://mlsanity.com/paper/2602.11072/) (2026)
- [Toward Machine Interpreting: Lessons from Human Interpreting Studies](https://mlsanity.com/paper/2508.07964/) (2025)
- [NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation](https://mlsanity.com/paper/2606.13121/) (2026)

## Abstract (arXiv)

Simultaneous Machine Translation (SiMT) generates translations while receiving streaming source inputs. This requires the SiMT model to learn a read/write policy, deciding when to translate and when to wait for more source input. Numerous linguistic studies indicate that audiences in SiMT scenarios have distinct preferences, such as accurate translations, simpler syntax, and no unnecessary latency. Aligning SiMT models with these human preferences is crucial to improve their performances. However, this issue still remains unexplored. Additionally, preference optimization for SiMT task is also challenging. Existing methods focus solely on optimizing the generated responses, ignoring human preferences related to latency and the optimization of read/write policy during the preference optimization phase. To address these challenges, we propose Simultaneous Preference Learning (SimulPL), a preference learning framework tailored for the SiMT task. In the SimulPL framework, we categorize SiMT human preferences into five aspects: translation quality preference, monotonicity preference, key point preference, simplicity preference, and latency preference. By leveraging the first four preferences, we construct human preference prompts to efficiently guide GPT-4/4o in generating preference data for the SiMT task. In the preference optimization phase, SimulPL integrates latency preference into the optimization objective and enables SiMT models to improve the read/write policy, thereby aligning with human preferences more effectively. Experimental results indicate that SimulPL exhibits better alignment with human preferences across all latency levels in ZhrightarrowEn, DerightarrowEn and EnrightarrowZh SiMT tasks. Our data and code will be available at https://github.com/EurekaForNLP/SimulPL.