mlsanityData to 14 Oct 2026

DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory

arXiv 2410.08143 ↗First posted 10 Oct 2024cs.CL cs.AIcited by 27

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing entire documents. In this paper, we introduce DelTA, a Document-levEL Translation Agent designed to overcome these limitations. DelTA features a multi-level memory structure that stores information across various granularities and spans, including Proper Noun Records, Bilingual Summary, Long-Term Memory, and Short-Term Memory, which are continuously retrieved and updated by auxiliary LLM-based components. Experimental results indicate that DelTA significantly outperforms strong baselines in terms of translation consistency and quality across four open/closed-source LLMs and two representative document translation datasets, achieving an increase in consistency scores by up to 4.58 percentage points and in COMET scores by up to 3.16 points on average. DelTA employs a sentence-by-sentence translation strategy, ensuring no sentence omissions and offering a memory-efficient solution compared to the mainstream method. Furthermore, DelTA improves pronoun and context-dependent translation accuracy, and the summary component of the agent also shows promise as a tool for query-based summarization tasks. The code and data of our approach are released at https://github.com/YutongWang1216/DocMTAgent.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 42 of its 53 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

42 of 53 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts20 May
  2. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 39

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  3. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  4. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  5. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
  6. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 348
  7. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 250
  8. 2024Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agentscited by 218
  9. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  10. 2023Is ChatGPT A Good Translator? Yes With GPT-4 As The Enginecited by 176
  11. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 146
  12. 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
27 more
  1. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  2. 2023Document-Level Machine Translation with Large Language Modelscited by 90
  3. 2017Evaluating Discourse Phenomena in Neural Machine Translationcited by 87
  4. 2018Document-Level Neural Machine Translation with Hierarchical Attention Networkscited by 85
  5. 2023Large language models effectively leverage document-level context for literary translation, but critical errors persistcited by 80
  6. 2018Improving the Transformer Translation Model with Document-Level Contextcited by 74
  7. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  8. 2024Adapting Large Language Models for Document-Level Machine Translationcited by 59
  9. 2022Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metriccited by 56
  10. 2023TIM: Teaching Large Language Models to Translate with Comparisoncited by 50
  11. 2017Exploiting Cross-Sentence Context for Neural Machine Translationcited by 48
  12. 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
  13. 2021G-Transformer for Document-level Machine Translationcited by 46
  14. 2019When and Why is Document-level Context Useful in Neural Machine Translation?cited by 45
  15. 2023Exploring Human-Like Translation Strategy with Large Language Modelscited by 44
  16. 2017Document Context Neural Machine Translation with Memory Networkscited by 41
  17. 2023LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedbackcited by 39
  18. 2024SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflectioncited by 34
  19. 2020Rethinking Document-level Neural Machine Translationcited by 32
  20. 2020Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translationcited by 27
  21. 2022Using natural language prompts for machine translationcited by 27
  22. 2024TasTe: Teaching Large Language Models to Translate through Self-Reflectioncited by 27
  23. 2023Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMscited by 25
  24. 2023Identifying Context-Dependent Translations for Evaluation Set Productioncited by 14
  25. 2022Focused Concatenation for Context-Aware Neural Machine Translationcited by 7
  26. 2022P-Transformer: Towards Better Document-to-Document Neural Machine Translationcited by 5
  27. 2024LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 16; 2026: 10.

27 papers.

Sort:

By area:

  1. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 83
  2. 2025Multilingual Contextualization of Large Language Models for Document-Level Machine Translationcited by 11
  3. 2025AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaborationcited by 10
  4. 2025Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAGcited by 7
  5. 2025Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translationcited by 6
  6. 2025Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinementcited by 5
  7. 2025NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMscited by 4
  8. 2025DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translationcited by 3
  9. 2025ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoningcited by 3
  10. 2024CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Modelscited by 2
  11. 2025Improving LLM-based Document-level Machine Translation with Multi-Knowledge Fusioncited by 2
  12. 2025GRAFT: A Graph-based Flow-aware Agentic Framework for Document-level Machine Translationcited by 2
15 more
  1. 2026Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translationcited by 2
  2. 2025LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordinationcited by 1
  3. 2025Discourse Graph Guided Document Translation with Large Language Modelscited by 1
  4. 2026Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selectioncited by 1
  5. 2026Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropycited by 1
  6. 2026STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translationcited by 1
  7. 2026Improving Term Evaluation in Machine Translation: Variation Matterscited by 1
  8. 2025Interpretable Style Takagi-Sugeno-Kang Fuzzy Clusteringcited by 0
  9. 2025Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Modelscited by 0
  10. 2025Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decodingcited by 0
  11. 2026Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Designcited by 0
  12. 2026G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translationcited by 0
  13. 2026Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunkingcited by 0
  14. 2026TermJudge: A Document-Level Metric Judging, Not Counting, Terminology in Machine Translation Evaluationcited by 0
  15. 2026Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing Document-Level Machine Translation via Filtered Synthetic Corpora and Two-Stage LLM Adaptation
  2. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
  3. 2026Why do Large Language Models Fail in Low-resource Translation? Unraveling the Token Dynamics of Large Language Models for Machine Translation
  4. 2025How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation
  5. 2024Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach
  6. 2024MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation
  7. 2024Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
  8. 2026Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets