# CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Models

arXiv: https://arxiv.org/abs/2410.21067 · HTML: https://mlsanity.com/paper/2410.21067/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

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

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [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)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://mlsanity.com/paper/2109.08678/) (2021)
- [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)
- [Improving Robustness of Machine Translation with Synthetic Noise](https://mlsanity.com/paper/1902.09508/) (2019)
- [Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View](https://mlsanity.com/paper/2203.12258/) (2022)
- [TasTe: Teaching Large Language Models to Translate through Self-Reflection](https://mlsanity.com/paper/2406.08434/) (2024)
- [DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory](https://mlsanity.com/paper/2410.08143/) (2024)
- [Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs](https://mlsanity.com/paper/2410.14057/) (2024)
- [Improving Large Language Models in Event Relation Logical Prediction](https://mlsanity.com/paper/2310.09158/) (2023)
- [Causal-Guided Active Learning for Debiasing Large Language Models](https://mlsanity.com/paper/2408.12942/) (2024)
- [Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance](https://mlsanity.com/paper/2205.02293/) (2022)
- [Context-Dependent Word Representation for Neural Machine Translation](https://mlsanity.com/paper/1607.00578/) (2016)

## Built on by (most cited first, 2 of 2)

- [TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration](https://mlsanity.com/paper/2506.08403/) (2025)
- [Causal MAS: A Survey of Large Language Model Architectures for Discovery and Effect Estimation](https://mlsanity.com/paper/2509.00987/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have shown great promise in machine translation, but they still struggle with contextually dependent terms, such as new or domain-specific words. This leads to inconsistencies and errors that are difficult to address. Existing solutions often depend on manual identification of such terms, which is impractical given the complexity and evolving nature of language. While Retrieval-Augmented Generation (RAG) could provide some assistance, its application to translation is limited by issues such as hallucinations from information overload. In this paper, we propose CRAT, a novel multi-agent translation framework that leverages RAG and causality-enhanced self-reflection to address these challenges. This framework consists of several specialized agents: the Unknown Terms Identification agent detects unknown terms within the context, the Knowledge Graph (KG) Constructor agent extracts relevant internal knowledge about these terms and retrieves bilingual information from external sources, the Causality-enhanced Judge agent validates the accuracy of the information, and the Translator agent incorporates the refined information into the final output. This automated process allows for more precise and consistent handling of key terms during translation. Our results show that CRAT significantly improves translation accuracy, particularly in handling context-sensitive terms and emerging vocabulary.