mlsanityData to 7 Oct 2026

Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges

arXiv 2511.04478 ↗First posted 6 Nov 2025cs.HC cs.AIcited by 2

On the map: Synthetic data and self-improvement for LLMs → LLM synthetic data generation

Abstract (arXiv)

The LLM-as-a-judge paradigm enables flexible, user-defined evaluation, but its effectiveness is often limited by the scarcity of diverse, representative data for refining criteria. We present a tool that integrates synthetic data generation into the LLM-as-a-judge workflow, empowering users to create tailored and challenging test cases with configurable domains, personas, lengths, and desired outcomes, including borderline cases. The tool also supports AI-assisted inline editing of existing test cases. To enhance transparency and interpretability, it reveals the prompts and explanations behind each generation. In a user study (N=24), 83% of participants preferred the tool over manually creating or selecting test cases, as it allowed them to rapidly generate diverse synthetic data without additional workload. The generated synthetic data proved as effective as hand-crafted data for both refining evaluation criteria and aligning with human preferences. These findings highlight synthetic data as a promising alternative, particularly in contexts where efficiency and scalability are critical.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 32 of its 73 references that are in the map. First posted on arXiv 6 Nov 2025.

Builds on

32 of 73 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personas28 Jun

Other references · 31

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  3. 2024A Survey on LLM-as-a-Judgecited by 1,384
  4. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  5. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  6. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 343
  7. 2024LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Taskscited by 236
  8. 2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 217
  9. 2024Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferencescited by 142
  10. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  11. 2013A Computational Approach to Politeness with Application to Social Factorscited by 104
  12. 2024Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Taskscited by 102
19 more
  1. 2024Can LLM be a Personalized Judge?cited by 99
  2. 2020Training Question Answering Models From Synthetic Datacited by 95
  3. 2023ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testingcited by 88
  4. 2023EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteriacited by 73
  5. 2024Self-Taught Evaluatorscited by 70
  6. 2022Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Expertscited by 54
  7. 2024Human-Centered Design Recommendations for LLM-as-a-Judgecited by 35
  8. 2024Finding Blind Spots in Evaluator LLMs with Interpretable Checklistscited by 32
  9. 2023Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Taskscited by 23
  10. 2024Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Coursecited by 19
  11. 2024Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AIcited by 18
  12. 2023DocLens: Multi-aspect Fine-grained Evaluation for Medical Text Generationcited by 16
  13. 2024Leveraging Large Language Models for Relevance Judgments in Legal Case Retrievalcited by 16
  14. 2024Designing Staged Evaluation Workflows for LLMs: Integrating Domain Experts, Lay Users, and Model-Generated Evaluation Criteriacited by 8
  15. 2024Toward Informal Language Processing: Knowledge of Slang in Large Language Modelscited by 6
  16. 2024Exploring Empty Spaces: Human-in-the-Loop Data Augmentationcited by 6
  17. 2024Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theoriescited by 4
  18. 2023PEANUT: A Human-AI Collaborative Tool for Annotating Audio-Visual Datacited by 2
  19. 2024Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundarycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 17
  2. 2026To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generationcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024JudgeBench: A Benchmark for Evaluating LLM-based Judges
  2. 2026LLM as a Meta-Judge: Synthetic Data for NLP Evaluation Metric Validation
  3. 2025Verdict: A Library for Scaling Judge-Time Compute
  4. 2024The Fellowship of the LLMs: Multi-Model Workflows for Synthetic Preference Optimization Dataset Generation
  5. 2025RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets
  6. 2025Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
  7. 2025When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs
  8. 2025Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems