mlsanityData to 14 Oct 2026

LLM Judges Can Be Too Generous When There Is No Reference Answer

arXiv 2607.12885 ↗First posted 14 Jul 2026cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

LLM judges are increasingly being used to evaluate open-ended model responses, often in no-reference settings where a ground-truth answer is unavailable. However, can they reliably assess in such evaluation setups? We explore this question in this paper through a two stage pipeline with a) calibration experiments that assess the judge model's knowledge of the task it is evaluating, and b) sensitivity experiments that assess how the judge model's performance is impacted by the presence and positioning of the reference answer in the prompt. Across experiments covering three languages, we show that the judge models we evaluated tend to over-credit incorrect answers in the absence of a reference answer, and adding reference answer information to the prompt flips the judge model's correct/incorrect decisions by as much as 85% in some experimental settings. Comparison with a subset of human annotations shows that these reference-driven changes generally align with human judgments. Our results emphasize the need for calibrating the LLM judges with a sample with reference-aware evaluation before using them in reference-free setups reliably, and our methodology provides a blueprint for researchers and practitioners in doing such calibration of LLM judges for other tasks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

34 of 50 references.

References · 34

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2024A Survey on LLM-as-a-Judgecited by 1,423
  5. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  6. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  7. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 494
  8. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 488
  9. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  10. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
  11. 2024Humans or LLMs as the Judge? A Study on Judgement Biasescited by 323
  12. 2024JudgeBench: A Benchmark for Evaluating LLM-based Judgescited by 318
22 more
  1. 2023Evaluating Large Language Models at Evaluating Instruction Followingcited by 302
  2. 2024Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judgecited by 269
  3. 2024Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judgescited by 205
  4. 2024Cognitive Bias in Decision-Making with LLMscited by 106
  5. 2024An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4cited by 94
  6. 2024CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklistscited by 94
  7. 2023Split and Merge: Aligning Position Biases in LLM-based Evaluatorscited by 72
  8. 2025Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineeringcited by 67
  9. 2025Neither Valid nor Reliable? Investigating the Use of LLMs as Judgescited by 39
  10. 2024Finding Blind Spots in Evaluator LLMs with Interpretable Checklistscited by 32
  11. 2025Beyond the Surface: Measuring Self-Preference in LLM Judgmentscited by 31
  12. 2024CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?cited by 30
  13. 2023Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Taskscited by 24
  14. 2025Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settingscited by 24
  15. 2024From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Taskscited by 22
  16. 2026Learning to Judge: LLMs Designing and Applying Evaluation Rubricscited by 19
  17. 2025Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluationcited by 18
  18. 2024Mitigating the Bias of Large Language Model Evaluationcited by 17
  19. 2025Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judgecited by 13
  20. 2026Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluationcited by 5
  21. 2026NLG Evaluation: Past, Present, Futurecited by 2
  22. 2025Towards Human-Like Grading: A Unified LLM-Enhanced Framework for Subjective Question Evaluationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Commit-first LLM judging inherits the judge's own errorscited by 2
  2. 2026Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passescited by 1
  3. 2026From Migration to Calibration: Aligning Agents with Deployment Requirementscited by 0
  4. 2026Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Argumentscited by 0