TransLLaMa: LLM-based Simultaneous Translation System
Not on the map. Why?
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.
Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 7 Feb 2024.
Builds on
29 of 49 references.
References · 29
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
- 2020Learning to summarize from human feedbackcited by 2,562
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
- 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
- 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
- 2023Prompting Large Language Models with Speech Recognition Abilitiescited by 139
- 2019Monotonic Infinite Lookback Attention for Simultaneous Machine Translationcited by 103
- 2016Learning to Translate in Real-time with Neural Machine Translationcited by 97
- 2020SimulEval: An Evaluation Toolkit for Simultaneous Translationcited by 94
17 more
- 2019Monotonic Multihead Attentioncited by 91
- 2016Can neural machine translation do simultaneous translation?cited by 85
- 2017Online and Linear-Time Attention by Enforcing Monotonic Alignmentscited by 85
- 2017Monotonic Chunkwise Attentioncited by 82
- 2020Efficient Wait-k Models for Simultaneous Machine Translationcited by 59
- 2022Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translationcited by 56
- 2018Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translationcited by 51
- 2020Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selectioncited by 47
- 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
- 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
- 2022Attention as a Guide for Simultaneous Speech Translationcited by 32
- 2022CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022cited by 30
- 2019Thinking Slow about Latency Evaluation for Simultaneous Machine Translationcited by 28
- 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 24
- 2023Learning Optimal Policy for Simultaneous Machine Translation via Binary Searchcited by 15
- 2023GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systemscited by 9
- 2023Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Datacited by 6
Built on by
Citing papers per year: 2024: 7; 2025: 16; 2026: 11.
34 papers.
Sort:
By area:
- 2025LLM Agents for Education: Advances and Applicationscited by 59
- 2024A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directionscited by 34
- 2024BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5cited by 18
- 2025Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulationcited by 13
- 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translationcited by 13
- 2025Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecturecited by 12
- 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translationcited by 11
- 2024LiveMind: Low-latency Large Language Models with Simultaneous Inferencecited by 10
- 2025Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agentscited by 9
- 2025LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encodingcited by 9
- 2025SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layerscited by 9
- 2024FASST: Fast LLM-based Simultaneous Speech Translationcited by 7
22 more
- 2025LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offlinecited by 5
- 2024Conversational SimulMT: Efficient Simultaneous Translation with Large Language Modelscited by 4
- 2025Large Language Models Are Read/Write Policy-Makers for Simultaneous Generationcited by 4
- 2025From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systemscited by 4
- 2025SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translationcited by 3
- 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Modelscited by 3
- 2025AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Datacited by 2
- 2025SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translationcited by 2
- 2024Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Mediacited by 1
- 2025Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknessescited by 1
- 2026Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategiescited by 1
- 2026Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approachescited by 1
- 2026Streaming Translation and Transcription Through Speech-to-Text Causal Alignmentcited by 1
- 2026MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translationcited by 1
- 2026Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speechcited by 1
- 2026Scaling Unsupervised Word Alignment to Documents via Structural Constraintscited by 1
- 2025Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategiescited by 0
- 2025OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusioncited by 0
- 2026RASST: Retrieval-Augmented Simultaneous Speech Translationcited by 0
- 2026Streaming Speech-to-Text Translation with a SpeechLLMcited by 0
- 2026MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation taskcited by 0
- 2026All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translationcited by 0
- 2026All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation24 Sep 2026
- 2026Scaling Unsupervised Word Alignment to Documents via Structural Constraints21 Aug 2026
- 2026MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task15 Jun 2026
- 2026Streaming Speech-to-Text Translation with a SpeechLLM14 May 2026
- 2026Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech22 Apr 2026
- 2026MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation6 Apr 2026
- 2026Streaming Translation and Transcription Through Speech-to-Text Causal Alignment12 Mar 2026
- 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models4 Mar 2026
- 2026Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches3 Mar 2026
- 2026RASST: Retrieval-Augmented Simultaneous Speech Translation30 Jan 2026
- 2026Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies16 Jan 2026
- 2025OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion28 Nov 2025
22 more
- 2025Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies26 Sep 2025
- 2025SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation11 Aug 2025
- 2025Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses7 Aug 2025
- 2025AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data24 Jul 2025
- 2025SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers9 Jul 2025
- 2025From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems5 Jun 2025
- 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation27 May 2025
- 2025LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding22 May 2025
- 2025SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation22 Apr 2025
- 2025Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecture16 Apr 2025
- 2025LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline13 Apr 2025
- 2025LLM Agents for Education: Advances and Applications14 Mar 2025
- 2025Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation11 Mar 2025
- 2025Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents25 Feb 2025
- 2025Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation1 Jan 2025
- 2024FASST: Fast LLM-based Simultaneous Speech Translation18 Aug 2024
- 2024BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T528 Jun 2024
- 2024LiveMind: Low-latency Large Language Models with Simultaneous Inference20 Jun 2024
- 2024A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions6 Jun 2024
- 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation16 May 2024
- 2024Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Media21 Feb 2024
- 2024Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models16 Feb 2024
- 2026RASST: Retrieval-Augmented Simultaneous Speech Translation30 Jan 2026
- 2024A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directionscited by 34
- 2024BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5cited by 18
- 2025Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecturecited by 12
- 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translationcited by 11
- 2024LiveMind: Low-latency Large Language Models with Simultaneous Inferencecited by 10
- 2025LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encodingcited by 9
- 2024FASST: Fast LLM-based Simultaneous Speech Translationcited by 7
- 2025LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offlinecited by 5
- 2024Conversational SimulMT: Efficient Simultaneous Translation with Large Language Modelscited by 4
- 2025Large Language Models Are Read/Write Policy-Makers for Simultaneous Generationcited by 4
- 2025From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systemscited by 4
- 2025SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translationcited by 3
12 most cited of 25 All 25 (JSON)
- 2026All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation24 Sep 2026
- 2026Scaling Unsupervised Word Alignment to Documents via Structural Constraints21 Aug 2026
- 2026MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task15 Jun 2026
- 2026Streaming Speech-to-Text Translation with a SpeechLLM14 May 2026
- 2026Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech22 Apr 2026
- 2026MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation6 Apr 2026
- 2026Streaming Translation and Transcription Through Speech-to-Text Causal Alignment12 Mar 2026
- 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models4 Mar 2026
- 2026Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies16 Jan 2026
- 2025OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion28 Nov 2025
- 2025Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies26 Sep 2025
- 2025SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation11 Aug 2025
12 newest of 25 All 25 (JSON)