mlsanityData to 13 Oct 2026

Evaluating Explanations: How much do explanations from the teacher aid students?

arXiv 2012.00893 ↗First posted 1 Dec 2020cs.CL cs.LGcited by 94

Not on the map. Why?

Abstract (arXiv)

While many methods purport to explain predictions by highlighting salient features, what aims these explanations serve and how they ought to be evaluated often go unstated. In this work, we introduce a framework to quantify the value of explanations via the accuracy gains that they confer on a student model trained to simulate a teacher model. Crucially, the explanations are available to the student during training, but are not available at test time. Compared to prior proposals, our approach is less easily gamed, enabling principled, automatic, model-agnostic evaluation of attributions. Using our framework, we compare numerous attribution methods for text classification and question answering, and observe quantitative differences that are consistent (to a moderate to high degree) across different student model architectures and learning strategies.

Key facts. Cited by 94 papers in the map (data through 13 Oct 2026). First posted on arXiv 1 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 23; 2022: 22; 2023: 22; 2024: 14; 2025: 9; 2026: 4.

94 papers.

Sort:

By area:

  1. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 719
  2. 2022Large Language Models Can Self-Improvecited by 659
  3. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 129
  4. 2023Training Language Models with Language Feedback at Scalecited by 126
  5. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  6. 2022Interpreting Language Models with Contrastive Explanationscited by 92
  7. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  8. 2021When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Datacited by 75
  9. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 75
  10. 2021ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoningcited by 58
  11. 2022PINTO: Faithful Language Reasoning Using Prompt-Generated Rationalescited by 56
  12. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
38 more
  1. 2022CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behaviorcited by 54
  2. 2021Do Input Gradients Highlight Discriminative Features?cited by 52
  3. 2022Training Language Models with Language Feedbackcited by 49
  4. 2021A Review on Explainability in Multimodal Deep Neural Netscited by 46
  5. 2024Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillationcited by 46
  6. 2023Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactualscited by 44
  7. 2023Quantifying Context Mixing in Transformerscited by 43
  8. 2021UNIREX: A Unified Learning Framework for Language Model Rationale Extractioncited by 32
  9. 2021On the Sensitivity and Stability of Model Interpretations in NLPcited by 30
  10. 2021Supervising Model Attention with Human Explanations for Robust Natural Language Inferencecited by 29
  11. 2021Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updatescited by 27
  12. 2021Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanationscited by 26
  13. 2023CREST: A Joint Framework for Rationalization and Counterfactual Text Generationcited by 24
  14. 2021Rissanen Data Analysis: Examining Dataset Characteristics via Description Lengthcited by 22
  15. 2022REV: Information-Theoretic Evaluation of Free-Text Rationalescited by 22
  16. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  17. 2023Tailoring Self-Rationalizers with Multi-Reward Distillationcited by 21
  18. 2022Learning to Scaffold: Optimizing Model Explanations for Teachingcited by 20
  19. 2022Use-Case-Grounded Simulations for Explanation Evaluationcited by 19
  20. 2023Can Authorship Representation Learning Capture Stylistic Features?cited by 17
  21. 2023Learning by Self-Explainingcited by 17
  22. 2021The Irrationality of Neural Rationale Modelscited by 16
  23. 2023Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalizationcited by 16
  24. 2021Counterfactual Evaluation for Explainable AIcited by 15
  25. 2022A survey on improving NLP models with human explanationscited by 15
  26. 2022ExSum: From Local Explanations to Model Understandingcited by 15
  27. 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Modelscited by 14
  28. 2021Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLUcited by 13
  29. 2021On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluationcited by 12
  30. 2021Thermostat: A Large Collection of NLP Model Explanations and Analysis Toolscited by 11
  31. 2022Logical Satisfiability of Counterfactuals for Faithful Explanations in NLIcited by 11
  32. 2023ALMANACS: A Simulatability Benchmark for Language Model Explainabilitycited by 11
  33. 2022A Psychological Theory of Explainabilitycited by 10
  34. 2022FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationalescited by 10
  35. 2023Goodhart's Law Applies to NLP's Explanation Benchmarkscited by 10
  36. 2021Efficient Explanations from Empirical Explainerscited by 9
  37. 2022Does Self-Rationalization Improve Robustness to Spurious Correlations?cited by 9
  38. 2021SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoningcited by 7

50 most cited of 94 All 94 (JSON)