mlsanityData to 13 Oct 2026

DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms

arXiv 2406.07232 ↗First posted 11 Jun 2024cs.CL cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection methods lack effective feedback information, limiting the translation performance. To address this, we introduce a DUAL-REFLECT framework, leveraging the dual learning of translation tasks to provide effective feedback, thereby enhancing the models' self-reflective abilities and improving translation performance. The application of this method across various translation tasks has proven its effectiveness in improving translation accuracy and eliminating ambiguities, especially in translation tasks with low-resource language pairs.

Key facts. Cited by 16 papers in the map (data through 13 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

14 of 31 references.

References · 14

  1. 2023GPT-4 Technical Reportcited by 18,278
  2. 2022Training language models to follow instructions with human feedbackcited by 15,856
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,156
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,541
  5. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,586
  6. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,200
  7. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,001
  8. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
  9. 2022Generating Sequences by Learning to Self-Correctcited by 273
  10. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 206
  11. 2016Dual Learning for Machine Translationcited by 146
  12. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
2 more
  1. 2023LLMs cannot find reasoning errors, but can correct them given the error locationcited by 85
  2. 2017Dual Supervised Learningcited by 33

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 4; 2025: 8; 2026: 4.

16 papers.

Sort:

By area:

  1. 2025Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysiscited by 26
  2. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  3. 2024Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answeringcited by 13
  4. 2025Generator-Assistant Stepwise Rollback Framework for Large Language Model Agentcited by 13
  5. 2024MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translationcited by 12
  6. 2025EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solvingcited by 10
  7. 2025DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimizationcited by 7
  8. 2024LLM-based Translation Inference with Iterative Bilingual Understandingcited by 6
  9. 2025Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinementcited by 5
  10. 2025A Review of Incorporating Psychological Theories in LLMscited by 5
  11. 2025Adaptive Inner Speech-Text Alignment for LLM-based Speech Translationcited by 2
  12. 2025Psychology-Driven Enhancement of Humour Translationcited by 0
4 more
  1. 2026CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Scriptcited by 0
  2. 2026Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translationcited by 0
  3. 2026PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translationcited by 0
  4. 2026Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agentscited by 0