mlsanityData to 7 Oct 2026

Reframing Human-AI Collaboration for Generating Free-Text Explanations

arXiv 2112.08674 ↗First posted 16 Dec 2021cs.CLcited by 125

Not on the map. Why?

Abstract (arXiv)

Large language models are increasingly capable of generating fluent-appearing text with relatively little task-specific supervision. But can these models accurately explain classification decisions? We consider the task of generating free-text explanations using human-written examples in a few-shot manner. We find that (1) authoring higher quality prompts results in higher quality generations; and (2) surprisingly, in a head-to-head comparison, crowdworkers often prefer explanations generated by GPT-3 to crowdsourced explanations in existing datasets. Our human studies also show, however, that while models often produce factual, grammatical, and sufficient explanations, they have room to improve along axes such as providing novel information and supporting the label. We create a pipeline that combines GPT-3 with a supervised filter that incorporates binary acceptability judgments from humans in the loop. Despite the intrinsic subjectivity of acceptability judgments, we demonstrate that acceptability is partially correlated with various fine-grained attributes of explanations. Our approach is able to consistently filter GPT-3-generated explanations deemed acceptable by humans.

Key facts. Cited by 125 papers in the map (data through 7 Oct 2026). Builds on 47 of its 69 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

47 of 69 references.

References · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  7. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  8. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  9. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  10. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  11. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  12. 2019How Can We Know What Language Models Know?cited by 953
35 more
  1. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  2. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  3. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  4. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  5. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  6. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  7. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  8. 2021True Few-Shot Learning with Language Modelscited by 343
  9. 2018Hypothesis Only Baselines in Natural Language Inferencecited by 291
  10. 2016Rationalizing Neural Predictionscited by 281
  11. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  12. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  13. 2018Textual Explanations for Self-Driving Vehiclescited by 226
  14. 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
  15. 2019Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasetscited by 173
  16. 2020Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AIcited by 166
  17. 2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
  18. 2020Measuring Association Between Labels and Free-Text Rationalescited by 159
  19. 2016Generating Visual Explanationscited by 156
  20. 2020WT5?! Training Text-to-Text Models to Explain their Predictionscited by 148
  21. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  22. 2020Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?cited by 95
  23. 2021e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Taskscited by 84
  24. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  25. 2019Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptionscited by 81
  26. 2021ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoningcited by 58
  27. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  28. 2017Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanationscited by 37
  29. 2021A Study of Automatic Metrics for the Evaluation of Natural Language Explanationscited by 34
  30. 2020Explaining Question Answering Models through Text Generationcited by 33
  31. 2021On the Diversity and Limits of Human Explanationscited by 30
  32. 2019How Decoding Strategies Affect the Verifiability of Generated Textcited by 27
  33. 2020Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervisioncited by 27
  34. 2021Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setupcited by 16
  35. 2020Harnessing Explanations to Bridge AI and Humanscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 26; 2023: 47; 2024: 27; 2025: 23; 2026: 2.

125 papers.

Sort:

By area:

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  3. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  4. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  5. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  6. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  7. 2022Can language models learn from explanations in context?cited by 248
  8. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  9. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 230
  10. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  11. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 154
  12. 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Stepcited by 144
38 more
  1. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  2. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  3. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 123
  4. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  5. 2023Text Classification via Large Language Modelscited by 104
  6. 2023SCOTT: Self-Consistent Chain-of-Thought Distillationcited by 103
  7. 2023VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Usecited by 100
  8. 2022Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contestcited by 98
  9. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
  10. 2022FLUTE: Figurative Language Understanding through Textual Explanationscited by 78
  11. 2023Large Language Models for Supply Chain Optimizationcited by 61
  12. 2022PINTO: Faithful Language Reasoning Using Prompt-Generated Rationalescited by 56
  13. 2023HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attributioncited by 55
  14. 2022NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Flycited by 48
  15. 2023Distilling Script Knowledge from Large Language Models for Constrained Language Planningcited by 45
  16. 2023Evaluating GPT-3 Generated Explanations for Hateful Content Moderationcited by 44
  17. 2025Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistenciescited by 39
  18. 2023Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationalescited by 37
  19. 2024INMS: Memory Sharing for Large Language Model based Agentscited by 31
  20. 2023HARE: Explainable Hate Speech Detection with Step-by-Step Reasoningcited by 30
  21. 2024Mechanistic?cited by 25
  22. 2024Properties and Challenges of LLM-Generated Explanationscited by 24
  23. 2022REV: Information-Theoretic Evaluation of Free-Text Rationalescited by 22
  24. 2023Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailmentcited by 22
  25. 2024LLM-Generated Black-box Explanations Can Be Adversarially Helpfulcited by 20
  26. 2022WeLM: A Well-Read Pre-trained Language Model for Chinesecited by 19
  27. 2024Understanding Figurative Meaning through Explainable Visual Entailmentcited by 19
  28. 2025VeriPlan: Integrating Formal Verification and LLMs into End-User Planningcited by 19
  29. 2022Generic Temporal Reasoning with Differential Analysis and Explanationcited by 18
  30. 2023TarGEN: Targeted Data Generation with Large Language Modelscited by 17
  31. 2024xTower: A Multilingual LLM for Explaining and Correcting Translation Errorscited by 17
  32. 2023Ecologically Valid Explanations for Label Variation in NLIcited by 16
  33. 2024LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanationscited by 16
  34. 2024Trustworthy and Practical AI for Healthcare: A Guided Deferral System with Large Language Modelscited by 16
  35. 2023Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalizationcited by 15
  36. 2023What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situationscited by 15
  37. 2024Position: Towards Bidirectional Human-AI Alignmentcited by 15
  38. 2024Investigating Mysteries of CoT-Augmented Distillationcited by 15

50 most cited of 125 All 125 (JSON)