mlsanityData to 7 Oct 2026

TransLLaMa: LLM-based Simultaneous Translation System

arXiv 2402.04636 ↗First posted 7 Feb 2024cs.CLcited by 34

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

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  8. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
  9. 2023Prompting Large Language Models with Speech Recognition Abilitiescited by 139
  10. 2019Monotonic Infinite Lookback Attention for Simultaneous Machine Translationcited by 103
  11. 2016Learning to Translate in Real-time with Neural Machine Translationcited by 97
  12. 2020SimulEval: An Evaluation Toolkit for Simultaneous Translationcited by 94
17 more
  1. 2019Monotonic Multihead Attentioncited by 91
  2. 2016Can neural machine translation do simultaneous translation?cited by 85
  3. 2017Online and Linear-Time Attention by Enforcing Monotonic Alignmentscited by 85
  4. 2017Monotonic Chunkwise Attentioncited by 82
  5. 2020Efficient Wait-k Models for Simultaneous Machine Translationcited by 59
  6. 2022Over-Generation Cannot Be Rewarded: Length-Adaptive Average Lagging for Simultaneous Speech Translationcited by 56
  7. 2018Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translationcited by 51
  8. 2020Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selectioncited by 47
  9. 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
  10. 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
  11. 2022Attention as a Guide for Simultaneous Speech Translationcited by 32
  12. 2022CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022cited by 30
  13. 2019Thinking Slow about Latency Evaluation for Simultaneous Machine Translationcited by 28
  14. 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 24
  15. 2023Learning Optimal Policy for Simultaneous Machine Translation via Binary Searchcited by 15
  16. 2023GPT-in-the-Loop: Adaptive Decision-Making for Multiagent Systemscited by 9
  17. 2023Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Datacited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 16; 2026: 11.

34 papers.

Sort:

By area:

  1. 2025LLM Agents for Education: Advances and Applicationscited by 59
  2. 2024A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directionscited by 34
  3. 2024BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5cited by 18
  4. 2025Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulationcited by 13
  5. 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translationcited by 13
  6. 2025Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecturecited by 12
  7. 2024Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translationcited by 11
  8. 2024LiveMind: Low-latency Large Language Models with Simultaneous Inferencecited by 10
  9. 2025Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agentscited by 9
  10. 2025LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encodingcited by 9
  11. 2025SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layerscited by 9
  12. 2024FASST: Fast LLM-based Simultaneous Speech Translationcited by 7
22 more
  1. 2025LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offlinecited by 5
  2. 2024Conversational SimulMT: Efficient Simultaneous Translation with Large Language Modelscited by 4
  3. 2025Large Language Models Are Read/Write Policy-Makers for Simultaneous Generationcited by 4
  4. 2025From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systemscited by 4
  5. 2025SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translationcited by 3
  6. 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Modelscited by 3
  7. 2025AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Datacited by 2
  8. 2025SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translationcited by 2
  9. 2024Bangla AI: A Framework for Machine Translation Utilizing Large Language Models for Ethnic Mediacited by 1
  10. 2025Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknessescited by 1
  11. 2026Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategiescited by 1
  12. 2026Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approachescited by 1
  13. 2026Streaming Translation and Transcription Through Speech-to-Text Causal Alignmentcited by 1
  14. 2026MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translationcited by 1
  15. 2026Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speechcited by 1
  16. 2026Scaling Unsupervised Word Alignment to Documents via Structural Constraintscited by 1
  17. 2025Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategiescited by 0
  18. 2025OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusioncited by 0
  19. 2026RASST: Retrieval-Augmented Simultaneous Speech Translationcited by 0
  20. 2026Streaming Speech-to-Text Translation with a SpeechLLMcited by 0
  21. 2026MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation taskcited by 0
  22. 2026All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translationcited by 0