mlsanityData to 7 Oct 2026

ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing

arXiv 2305.09770 ↗First posted 16 May 2023cs.HC cs.AI cs.CLcited by 31

Not on the map. Why?

Abstract (arXiv)

Despite a surge collection of XAI methods, users still struggle to obtain required AI explanations. Previous research suggests chatbots as dynamic solutions, but the effective design of conversational XAI agents for practical human needs remains under-explored. This paper focuses on Conversational XAI for AI-assisted scientific writing tasks. Drawing from human linguistic theories and formative studies, we identify four design rationales: "multifaceted", "controllability", "mix-initiative", "context-aware drill-down". We incorporate them into an interactive prototype, ConvXAI, which facilitates heterogeneous AI explanations for scientific writing through dialogue. In two studies with 21 users, ConvXAI outperforms a GUI-based baseline on improving human-perceived understanding and writing improvement. The paper further discusses the practical human usage patterns in interacting with ConvXAI for scientific co-writing.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 57 of its 93 references that are in the map. First posted on arXiv 16 May 2023.

Builds on

57 of 93 references.

References · 57

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  6. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  7. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  8. 2018Datasheets for Datasetscited by 1,371
  9. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  10. 2018Model Cards for Model Reportingcited by 1,068
  11. 2018CoQA: A Conversational Question Answering Challengecited by 674
  12. 2019Attention is not not Explanationcited by 629
38 more
  1. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  2. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  3. 2020Towards a Human-like Open-Domain Chatbotcited by 467
  4. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  5. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  6. 2016Rationalizing Neural Predictionscited by 281
  7. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  8. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
  9. 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 245
  10. 2016Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Taskscited by 216
  11. 2020Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?cited by 189
  12. 2017ParlAI: A Dialog Research Software Platformcited by 139
  13. 2020The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?cited by 122
  14. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 105
  15. 2017Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciencescited by 84
  16. 2019ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisonscited by 83
  17. 2019AllenNLP Interpret: A Framework for Explaining Predictions of NLP Modelscited by 74
  18. 2020How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Maskingcited by 63
  19. 2021Can We Automate Scientific Reviewing?cited by 63
  20. 2018Did the Model Understand the Question?cited by 60
  21. 2021Explanation-Based Human Debugging of NLP Models: A Surveycited by 53
  22. 2017The Promise and Peril of Human Evaluation for Model Interpretabilitycited by 52
  23. 2018What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Playcited by 52
  24. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  25. 2019Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Studycited by 47
  26. 2020Towards Transparent and Explainable Attention Modelscited by 47
  27. 2020Conceptual Metaphors Impact Perceptions of Human-AI Collaborationcited by 47
  28. 2022Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revisioncited by 46
  29. 2020Interpretation of NLP models through input marginalizationcited by 43
  30. 2021Wordcraft: a Human-AI Collaborative Editor for Story Writingcited by 41
  31. 2020How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labelscited by 39
  32. 2020Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Predictioncited by 36
  33. 2021An Empirical Comparison of Instance Attribution Methods for NLPcited by 35
  34. 2017Iris: A Conversational Agent for Complex Taskscited by 22
  35. 2020Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experiencecited by 20
  36. 2022How do you Converse with an Analytical Chatbot? Revisiting Gricean Maxims for Designing Analytical Conversational Behaviorcited by 20
  37. 2021Dissonance Between Human and Machine Understandingcited by 18
  38. 2020Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QAcited by 17

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 9; 2025: 12; 2026: 7.

31 papers.

Sort:

By area:

  1. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
  2. 2025LLMs for Explainable AI: A Comprehensive Surveycited by 42
  3. 2024IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedbackcited by 40
  4. 2024CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledgecited by 28
  5. 2025Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistantcited by 26
  6. 2024LLMs for XAI: Future Directions for Explaining Explanationscited by 19
  7. 2024LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanationscited by 16
  8. 2024PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideationcited by 16
  9. 2025Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Processcited by 14
  10. 2024Not Just Novelty: A Longitudinal Study on Utility and Customization of an AI Workflowcited by 13
  11. 2024Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Toolscited by 13
  12. 2023InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanationscited by 11
19 more
  1. 2025Where Do I 'Add the Egg'?: Exploring Agency and Ownership in AI Creative Co-Writing Systemscited by 7
  2. 2024Explingo: Explaining AI Predictions using Large Language Modelscited by 6
  3. 2023May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainabilitycited by 5
  4. 2024CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systemscited by 5
  5. 2025StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Frameworkcited by 4
  6. 2026Narrix: Remixing Narrative Strategies from Examples for Story Writingcited by 4
  7. 2025Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decompositioncited by 3
  8. 2026An Agentic Approach to Generating XAI-Narrativescited by 3
  9. 2025Show Me How: Benefits and Challenges of Agent-Augmented Counterfactual Explanations for Non-Expert Userscited by 2
  10. 2025Let's Get You Hired: A Job Seeker's Perspective on Multi-Agent Recruitment Systems for Explaining Hiring Decisionscited by 2
  11. 2023Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Modelcited by 1
  12. 2025Conversational Explanations: Discussing Explainable AI with Non-AI Expertscited by 1
  13. 2026Designing Proactive Thought Partners for Writingcited by 1
  14. 2025AI Ethics and Social Norms: Exploring ChatGPT's Capabilities From What to Howcited by 0
  15. 2025Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systemscited by 0
  16. 2026Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planningcited by 0
  17. 2026Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AIcited by 0
  18. 2026Can Conversational XAI Improve User Performance? An Experimental Studycited by 0
  19. 2026Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliancecited by 0