# TransLLaMa: LLM-based Simultaneous Translation System

arXiv: https://arxiv.org/abs/2402.04636 · HTML: https://mlsanity.com/paper/2402.04636/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 7 Feb 2024.

## Builds on (most cited first, 29 of 29)

- [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)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [Prompting Large Language Models with Speech Recognition Abilities](https://mlsanity.com/paper/2307.11795/) (2023)
- [Monotonic Infinite Lookback Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.05218/) (2019)
- [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)
- [Online and Linear-Time Attention by Enforcing Monotonic Alignments](https://mlsanity.com/paper/1704.00784/) (2017)
- [Monotonic Chunkwise Attention](https://mlsanity.com/paper/1712.05382/) (2017)
- [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)
- [Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation](https://mlsanity.com/paper/1806.03661/) (2018)
- [Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection](https://mlsanity.com/paper/2005.11185/) (2020)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy](https://mlsanity.com/paper/2109.05238/) (2021)
- [Attention as a Guide for Simultaneous Speech Translation](https://mlsanity.com/paper/2212.07850/) (2022)
- [CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022](https://mlsanity.com/paper/2204.06028/) (2022)
- [Thinking Slow about Latency Evaluation for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.00048/) (2019)
- [Hidden Markov Transformer for Simultaneous Machine Translation](https://mlsanity.com/paper/2303.00257/) (2023)
- [Learning Optimal Policy for Simultaneous Machine Translation via Binary Search](https://mlsanity.com/paper/2305.12774/) (2023)
- [GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systems](https://mlsanity.com/paper/2308.10435/) (2023)
- [Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data](https://mlsanity.com/paper/2306.08582/) (2023)

## Built on by (most cited first, 30 of 34)

- [LLM Agents for Education: Advances and Applications](https://mlsanity.com/paper/2503.11733/) (2025)
- [A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions](https://mlsanity.com/paper/2406.03712/) (2024)
- [BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5](https://mlsanity.com/paper/2406.19954/) (2024)
- [Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation](https://mlsanity.com/paper/2503.08195/) (2025)
- [SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation](https://mlsanity.com/paper/2505.20622/) (2025)
- [Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture](https://mlsanity.com/paper/2504.11809/) (2025)
- [Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation](https://mlsanity.com/paper/2405.10443/) (2024)
- [LiveMind: Low-latency Large Language Models with Simultaneous Inference](https://mlsanity.com/paper/2406.14319/) (2024)
- [Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents](https://mlsanity.com/paper/2502.17967/) (2025)
- [LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding](https://mlsanity.com/paper/2505.16983/) (2025)
- [SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers](https://mlsanity.com/paper/2507.06517/) (2025)
- [FASST: Fast LLM-based Simultaneous Speech Translation](https://mlsanity.com/paper/2408.09430/) (2024)
- [From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems](https://mlsanity.com/paper/2506.04565/) (2025)
- [Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation](https://mlsanity.com/paper/2501.00868/) (2025)
- [LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline](https://mlsanity.com/paper/2504.09570/) (2025)
- [Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models](https://mlsanity.com/paper/2402.10552/) (2024)
- [SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation](https://mlsanity.com/paper/2504.15509/) (2025)
- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data](https://mlsanity.com/paper/2507.18442/) (2025)
- [SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation](https://mlsanity.com/paper/2508.07781/) (2025)
- [Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Media](https://mlsanity.com/paper/2402.14179/) (2024)
- [Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses](https://mlsanity.com/paper/2508.05009/) (2025)
- [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2601.11002/) (2026)
- [Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches](https://mlsanity.com/paper/2603.02655/) (2026)
- [Streaming Translation and Transcription Through Speech-to-Text Causal Alignment](https://mlsanity.com/paper/2603.11578/) (2026)
- [MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation](https://mlsanity.com/paper/2604.04839/) (2026)
- [Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech](https://mlsanity.com/paper/2604.21045/) (2026)
- [Scaling Unsupervised Word Alignment to Documents via Structural Constraints](https://mlsanity.com/paper/2608.21023/) (2026)
- [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2509.21801/) (2025)
- [OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion](https://mlsanity.com/paper/2512.00234/) (2025)

## Abstract (arXiv)

Decoder-only large language models (LLMs) have recently demonstrated impressive capabilities in text generation and reasoning. Nonetheless, they have limited applications in simultaneous machine translation (SiMT), currently dominated by encoder-decoder transformers. This study demonstrates that, after fine-tuning on a small dataset comprising causally aligned source and target sentence pairs, a pre-trained open-source LLM can control input segmentation directly by generating a special "wait" token. This obviates the need for a separate policy and enables the LLM to perform English-German and English-Russian SiMT tasks with BLEU scores that are comparable to those of specific state-of-the-art baselines. We also evaluated closed-source models such as GPT-4, which displayed encouraging results in performing the SiMT task without prior training (zero-shot), indicating a promising avenue for enhancing future SiMT systems.