# M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation

arXiv: https://arxiv.org/abs/2412.20127 · HTML: https://mlsanity.com/paper/2412.20127/

## Key facts

- Cited by 13 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 24 of its 41 references that are in the map.
- First posted on arXiv 28 Dec 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 24 of 24)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation](https://mlsanity.com/paper/2104.14478/) (2021)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2209.06243/) (2022)
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024)
- [GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4](https://mlsanity.com/paper/2310.13988/) (2023)
- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation](https://mlsanity.com/paper/2308.07286/) (2023)
- [LLMaAA: Making Large Language Models as Active Annotators](https://mlsanity.com/paper/2310.19596/) (2023)
- [Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration](https://mlsanity.com/paper/2305.14324/) (2023)
- [The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation](https://mlsanity.com/paper/2405.01299/) (2024)
- [Can Automatic Metrics Assess High-Quality Translations?](https://mlsanity.com/paper/2405.18348/) (2024)
- [PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation](https://mlsanity.com/paper/2406.18528/) (2024)
- [From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation](https://mlsanity.com/paper/2403.14118/) (2024)

## Built on by (most cited first, 13 of 13)

- [Agent-as-a-Judge](https://mlsanity.com/paper/2601.05111/) (2026)
- [RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation](https://mlsanity.com/paper/2603.20882/) (2026)
- [Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation](https://mlsanity.com/paper/2504.01919/) (2025)
- [MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs](https://mlsanity.com/paper/2510.22967/) (2025)
- [Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition](https://mlsanity.com/paper/2603.18557/) (2026)
- [GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation](https://mlsanity.com/paper/2604.24929/) (2026)
- [CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate](https://mlsanity.com/paper/2511.22854/) (2025)
- [RevoNAD: Reflective Evolutionary Exploration for Neural Architecture Design](https://mlsanity.com/paper/2512.05403/) (2025)
- [Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations](https://mlsanity.com/paper/2512.18906/) (2025)
- [ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios](https://mlsanity.com/paper/2601.03011/) (2026)
- [AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization](https://mlsanity.com/paper/2605.08704/) (2026)
- [Source-Free MT Evaluation Is Not MT Evaluation](https://mlsanity.com/paper/2608.20925/) (2026)
- [EviSI: An Evidence-Based Evaluation Agent for Simultaneous Interpreting](https://mlsanity.com/paper/2609.08171/) (2026)

## Abstract (arXiv)

Recent advancements in large language models (LLMs) have given rise to the LLM-as-a-judge paradigm, showcasing their potential to deliver human-like judgments. However, in the field of machine translation (MT) evaluation, current LLM-as-a-judge methods fall short of learned automatic metrics. In this paper, we propose Multidimensional Multi-Agent Debate (M-MAD), a systematic LLM-based multi-agent framework for advanced LLM-as-a-judge MT evaluation. Our findings demonstrate that M-MAD achieves significant advancements by (1) decoupling heuristic MQM criteria into distinct evaluation dimensions for fine-grained assessments; (2) employing multi-agent debates to harness the collaborative reasoning capabilities of LLMs; (3) synthesizing dimension-specific results into a final evaluation judgment to ensure robust and reliable outcomes. Comprehensive experiments show that M-MAD not only outperforms all existing LLM-as-a-judge methods but also competes with state-of-the-art reference-based automatic metrics, even when powered by a suboptimal model like GPT-4o mini. Detailed ablations and analysis highlight the superiority of our framework design, offering a fresh perspective for LLM-as-a-judge paradigm. Our code and data are publicly available at https://github.com/SU-JIAYUAN/M-MAD.