# TasTe: Teaching Large Language Models to Translate through Self-Reflection

arXiv: https://arxiv.org/abs/2406.08434 · HTML: https://mlsanity.com/paper/2406.08434/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [In-context Examples Selection for Machine Translation](https://mlsanity.com/paper/2212.02437/) (2022)
- [Prompting PaLM for Translation: Assessing Strategies and Performance](https://mlsanity.com/paper/2211.09102/) (2022)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [TIM: Teaching Large Language Models to Translate with Comparison](https://mlsanity.com/paper/2307.04408/) (2023)
- [MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators](https://mlsanity.com/paper/2110.06609/) (2021)
- [Using natural language prompts for machine translation](https://mlsanity.com/paper/2202.11822/) (2022)
- [Deliberate then Generate: Enhanced Prompting Framework for Text Generation](https://mlsanity.com/paper/2305.19835/) (2023)

## Built on by (most cited first, 27 of 27)

- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning](https://mlsanity.com/paper/2504.10160/) (2025)
- [From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions](https://mlsanity.com/paper/2410.08197/) (2024)
- [DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory](https://mlsanity.com/paper/2410.08143/) (2024)
- [R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning](https://mlsanity.com/paper/2502.19735/) (2025)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association](https://mlsanity.com/paper/2505.15196/) (2025)
- [EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving](https://mlsanity.com/paper/2506.02672/) (2025)
- [A Survey of Calibration Process for Black-Box LLMs](https://mlsanity.com/paper/2412.12767/) (2024)
- [A Review of Incorporating Psychological Theories in LLMs](https://mlsanity.com/paper/2505.00003/) (2025)
- [WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation](https://mlsanity.com/paper/2503.19065/) (2025)
- [Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks](https://mlsanity.com/paper/2505.19806/) (2025)
- [AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs](https://mlsanity.com/paper/2507.18584/) (2025)
- [CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Models](https://mlsanity.com/paper/2410.21067/) (2024)
- [Contextual Memory Intelligence -- A Foundational Paradigm for Human-AI Collaboration and Reflective Generative AI Systems](https://mlsanity.com/paper/2506.05370/) (2025)
- [Self-reflecting Large Language Models: A Hegelian Dialectical Approach](https://mlsanity.com/paper/2501.14917/) (2025)
- [Code-Driven Inductive Synthesis: Enhancing Reasoning Abilities of Large Language Models with Sequences](https://mlsanity.com/paper/2503.13109/) (2025)
- [SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Management](https://mlsanity.com/paper/2510.08948/) (2025)
- [ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework](https://mlsanity.com/paper/2604.07506/) (2026)
- [Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection](https://mlsanity.com/paper/2605.30274/) (2026)
- [Interpretable Style Takagi-Sugeno-Kang Fuzzy Clustering](https://mlsanity.com/paper/2504.05125/) (2025)
- [Enhancing Large Language Models'Machine Translation via Dynamic Focus Anchoring](https://mlsanity.com/paper/2505.23140/) (2025)
- [An Interactive Multi-Agent System for Evaluation of New Product Concepts](https://mlsanity.com/paper/2603.05980/) (2026)
- [ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation](https://mlsanity.com/paper/2604.19144/) (2026)
- [CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script](https://mlsanity.com/paper/2607.05849/) (2026)
- [Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation](https://mlsanity.com/paper/2607.29287/) (2026)
- [PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine Translation](https://mlsanity.com/paper/2608.03077/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. Techniques like instruction tuning have effectively enhanced the proficiency of LLMs in the downstream task of machine translation. However, the existing approaches fail to yield satisfactory translation outputs that match the quality of supervised neural machine translation (NMT) systems. One plausible explanation for this discrepancy is that the straightforward prompts employed in these methodologies are unable to fully exploit the acquired instruction-following capabilities. To this end, we propose the TasTe framework, which stands for translating through self-reflection. The self-reflection process includes two stages of inference. In the first stage, LLMs are instructed to generate preliminary translations and conduct self-assessments on these translations simultaneously. In the second stage, LLMs are tasked to refine these preliminary translations according to the evaluation results. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods. Our work presents a promising approach to unleash the potential of LLMs and enhance their capabilities in MT. The codes and datasets are open-sourced at https://github.com/YutongWang1216/ReflectionLLMMT.