mlsanityData to 7 Oct 2026

Beyond Testers' Biases: Guiding Model Testing with Knowledge Bases using LLMs

arXiv 2310.09668 ↗First posted 14 Oct 2023cs.CL cs.SEcited by 9

Not on the map. Why?

Abstract (arXiv)

Current model testing work has mostly focused on creating test cases. Identifying what to test is a step that is largely ignored and poorly supported. We propose Weaver, an interactive tool that supports requirements elicitation for guiding model testing. Weaver uses large language models to generate knowledge bases and recommends concepts from them interactively, allowing testers to elicit requirements for further testing. Weaver provides rich external knowledge to testers and encourages testers to systematically explore diverse concepts beyond their own biases. In a user study, we show that both NLP experts and non-experts identified more, as well as more diverse concepts worth testing when using Weaver. Collectively, they found more than 200 failing test cases for stance detection with zero-shot ChatGPT. Our case studies further show that Weaver can help practitioners test models in real-world settings, where developers define more nuanced application scenarios (e.g., code understanding and transcript summarization) using LLMs.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 34 of its 70 references that are in the map. First posted on arXiv 14 Oct 2023.

Builds on

34 of 70 references.

References · 34

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  4. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  5. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  6. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  7. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  8. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  9. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 485
  10. 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
  11. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  12. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 215
22 more
  1. 2018Stress Test Evaluation for Natural Language Inferencecited by 211
  2. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
  3. 2022Domino: Discovering Systematic Errors with Cross-Modal Embeddingscited by 155
  4. 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137
  5. 2021Robustness Gym: Unifying the NLP Evaluation Landscapecited by 107
  6. 2020Language Models are Open Knowledge Graphscited by 95
  7. 2023NLPositionality: Characterizing Design Biases of Datasets and Modelscited by 91
  8. 2019Problem Formulation and Fairnesscited by 85
  9. 2023Crawling the Internal Knowledge-Base of Language Modelscited by 85
  10. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  11. 2021NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentationcited by 72
  12. 2021Collaboration Challenges in Building ML-Enabled Systems: Communication, Documentation, Engineering, and Processcited by 56
  13. 2021Changing the World by Changing the Datacited by 51
  14. 2019Requirements Engineering for Machine Learning: Perspectives from Data Scientistscited by 49
  15. 2023Supporting Human-AI Collaboration in Auditing LLMs with LLMscited by 46
  16. 2022Adaptive Testing of Computer Vision Modelscited by 39
  17. 2023Boosted Prompt Ensembles for Large Language Modelscited by 36
  18. 2023Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learningcited by 33
  19. 2022Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practicecited by 30
  20. 2023A Meta-Summary of Challenges in Building Products with ML Components -- Collecting Experiences from 4758+ Practitionerscited by 22
  21. 2023Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Designcited by 15
  22. 2022Capabilities for Better ML Engineeringcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 6; 2025: 2.

9 papers.

  1. 2025What Prompts Don't Say: Understanding and Managing Underspecification in LLM Promptscited by 32
  2. 2024Navigating LLM Ethics: Advancements, Challenges, and Future Directionscited by 28
  3. 2024What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Usecited by 24
  4. 2023(Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIscited by 21
  5. 2025SPHERE: An Evaluation Card for Human-AI Systemscited by 9
  6. 2024Clarify: Improving Model Robustness With Natural Language Correctionscited by 8
  7. 2024LLMs for Test Input Generation for Semantic Cachescited by 4
  8. 2024MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Modelscited by 1
  9. 2024What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicingcited by 0