mlsanityData to 14 Oct 2026

Are Bias Evaluation Methods Biased ?

arXiv 2506.17111 ↗First posted 20 Jun 2025cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

The creation of benchmarks to evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias, harmful behavior etc. Independent benchmarks adopt different approaches with distinct data sets and evaluation methods. We investigate how robust such benchmarks are by using different approaches to rank a set of representative models for bias and compare how similar are the overall rankings. We show that different but widely used bias evaluations methods result in disparate model rankings. We conclude with recommendations for the community in the usage of such benchmarks.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 21 of its 38 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

21 of 38 references.

References · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  5. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  6. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  7. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  8. 2024LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Taskscited by 243
  9. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  10. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  11. 2020Intrinsic Bias Metrics Do Not Correlate with Application Biascited by 148
  12. 2013A Theoretical Analysis of NDCG Type Ranking Measurescited by 119
9 more
  1. 2023KoBBQ: Korean Bias Benchmark for Question Answeringcited by 71
  2. 2022Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agentscited by 62
  3. 2024Large Language Model Safety: A Holistic Surveycited by 59
  4. 2023Social Bias Probing: Fairness Benchmarking for Language Modelscited by 32
  5. 2024Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBenchcited by 27
  6. 2023Mitigating Biases for Instruction-following Language Models via Bias Neurons Eliminationcited by 23
  7. 2024Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AIcited by 18
  8. 2023Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvementscited by 14
  9. 2021On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Servicescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMscited by 7
  2. 2026Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Biascited by 4
  3. 2025Measuring Algorithmic Partisanship via Zero-Shot Classification and Its Implications on Political Discoursecited by 0
  4. 2025Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluationcited by 0