mlsanityData to 7 Oct 2026

Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents

arXiv 2602.01405 ↗First posted 1 Feb 2026cs.HCcited by 4

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

also in 1 more
Abstract (arXiv)

High-quality feedback is essential for effective human-AI interaction. It bridges knowledge gaps, corrects digressions, and shapes system behavior; both during interaction and throughout model development. Yet despite its importance, human feedback to AI is often infrequent and low quality. This gap motivates a critical examination of human feedback during interactions with AIs. To understand and overcome the challenges preventing users from giving high-quality feedback, we conducted two studies examining feedback dynamics between humans and conversational agents (CAs). Our formative study, through the lens of Grice's maxims, identified four Feedback Barriers -- Common Ground, Verifiability, Communication, and Informativeness -- that prevent high-quality feedback by users. Building on these findings, we derive three design desiderata and show that systems incorporating scaffolds aligned with these desiderata enabled users to provide higher-quality feedback. Finally, we detail a call for action to the broader AI community for advances in Large Language Models capabilities to overcome Feedback Barriers.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 81 of its 161 references that are in the map. First posted on arXiv 1 Feb 2026.

Builds on

81 of 161 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy11 Jun

Other references · 80

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  6. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,081
  7. 2023Towards Understanding Sycophancy in Language Modelscited by 988
  8. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  9. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  10. 2024A Survey on Large Language Models for Code Generationcited by 646
  11. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  12. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 612
38 more
  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  2. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 428
  3. 2025LLMs Get Lost In Multi-Turn Conversationcited by 400
  4. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 272
  5. 2025Why Language Models Hallucinatecited by 205
  6. 2024Disentangling Length from Quality in Direct Preference Optimizationcited by 194
  7. 2024Large Language Models for Education: A Survey and Outlookcited by 185
  8. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 171
  9. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 167
  10. 2017A Survey on Dialogue Systems: Recent Advances and New Frontierscited by 162
  11. 2023Cultural Bias and Cultural Alignment of Large Language Modelscited by 149
  12. 2020A Survey on Conversational Recommender Systemscited by 142
  13. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 117
  14. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 116
  15. 2024Emergent social conventions and collective bias in LLM populationscited by 115
  16. 2025A Comprehensive Survey on Long Context Language Modelingcited by 113
  17. 2024What Large Language Models Know and What People Think They Knowcited by 109
  18. 2024When combinations of humans and AI are useful: A systematic review and meta-analysiscited by 100
  19. 2024CriticBench: Benchmarking LLMs for Critique-Correct Reasoningcited by 88
  20. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  21. 2020Recent Advances and Challenges in Task-oriented Dialog Systemcited by 78
  22. 2024LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QAcited by 78
  23. 2024Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encodingcited by 72
  24. 2024Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questionscited by 70
  25. 2023Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generationcited by 55
  26. 2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
  27. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 53
  28. 2024Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Trainingcited by 53
  29. 2025Why human-AI relationships need socioaffective alignmentcited by 47
  30. 2025PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistantscited by 44
  31. 2017Machine Teaching: A New Paradigm for Building Machine Learning Systemscited by 41
  32. 2021Putting Humans in the Natural Language Processing Loop: A Surveycited by 40
  33. 2024A Taxonomy for Human-LLM Interaction Modes: An Initial Explorationcited by 38
  34. 2024Learning to Ask: When LLM Agents Meet Unclear Instructioncited by 38
  35. 2024WildFeedback: Aligning LLMs With In-situ User Interactions And Feedbackcited by 31
  36. 2025Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQLcited by 30
  37. 2023Selective Explanations: Leveraging Human Input to Align Explainable AIcited by 29
  38. 2023The Trickle-down Impact of Reward (In-)consistency on RLHFcited by 29

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversationscited by 2
  2. 2026Caring Without Feeling: Affective Dynamics as the Control Layer of Human-AI Agent Collaborationcited by 1
  3. 2026MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Productioncited by 0
  4. 2026Gricea: An Open Science Platform for Conversational AI Researchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024The Future of Open Human Feedback
  2. 2024Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework
  3. 2025Agentic Workflows for Conversational Human-AI Interaction Design
  4. 2024Challenges in Human-Agent Communication
  5. 2024Comparing Rationality Between Large Language Models and Humans: Insights and Open Questions
  6. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
  7. 2024Constraining Participation: Affordances of Feedback Features in Interfaces to Large Language Models ↗
  8. 2026What Are You Doing? Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing