mlsanityData to 7 Oct 2026

ExpBERT: Representation Engineering with Natural Language Explanations

arXiv 2005.01932 ↗First posted 5 May 2020cs.CL cs.LG stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

Suppose we want to specify the inductive bias that married couples typically go on honeymoons for the task of extracting pairs of spouses from text. In this paper, we allow model developers to specify these types of inductive biases as natural language explanations. We use BERT fine-tuned on MultiNLI to ``interpret'' these explanations with respect to the input sentence, producing explanation-guided representations of the input. Across three relation extraction tasks, our method, ExpBERT, matches a BERT baseline but with 3--20x less labeled data and improves on the baseline by 3--10 F1 points with the same amount of labeled data.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 4; 2024: 3; 2025: 0; 2026: 1.

28 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022A Survey of Knowledge Enhanced Pre-trained Language Modelscited by 76
  3. 2021When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Datacited by 75
  4. 2021AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuningcited by 48
  5. 2021Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similaritycited by 35
  6. 2022Fixing Model Bugs with Natural Language Patchescited by 32
  7. 2023Large Language Model Instruction Following: A Survey of Progresses and Challengescited by 31
  8. 2021Supervising Model Attention with Human Explanations for Robust Natural Language Inferencecited by 29
  9. 2022Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deploymentcited by 25
  10. 2022Understanding and Enhancing Robustness of Concept-based Modelscited by 22
  11. 2021A Review of Text Style Transfer using Deep Learningcited by 18
  12. 2022A survey on improving NLP models with human explanationscited by 15
16 more
  1. 2022SsciBERT: A Pre-trained Language Model for Social Science Textscited by 12
  2. 2023Using Natural Language Explanations to Rescale Human Judgmentscited by 11
  3. 2022CLUES: A Benchmark for Learning Classifiers using Natural Language Explanationscited by 9
  4. 2022Automatic Concept Extraction for Concept Bottleneck-based Video Classificationcited by 8
  5. 2024A Self-explaining Neural Architecture for Generalizable Concept Learningcited by 3
  6. 2021Enhancing Natural Language Representation with Large-Scale Out-of-Domain Commonsensecited by 2
  7. 2022SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalizationcited by 2
  8. 2023Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifierscited by 2
  9. 2024Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillationcited by 2
  10. 2026Improving Attributed Long-form Question Answering with Intent Awarenesscited by 2
  11. 2021Open Rule Inductioncited by 1
  12. 2021Teach me how to Label: Labeling Functions from Natural Language with Text-to-text Transformerscited by 0
  13. 2021Bootstrapping Relation Extractors using Syntactic Search by Examplescited by 0
  14. 2021Technical Language Supervision for Intelligent Fault Diagnosis in Process Industrycited by 0
  15. 2023Exploring Automatically Perturbed Natural Language Explanations in Relation Extractioncited by 0
  16. 2024Reading Is Believing: Revisiting Language Bottleneck Models for Image Classificationcited by 0