mlsanityData to 14 Oct 2026

FLamE: Few-shot Learning from Natural Language Explanations

arXiv 2306.08042 ↗First posted 13 Jun 2023cs.CL cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Natural language explanations have the potential to provide rich information that in principle guides model reasoning. Yet, recent work by Lampinen et al. (2022) has shown limited utility of natural language explanations in improving classification. To effectively learn from explanations, we present FLamE, a two-stage few-shot learning framework that first generates explanations using GPT-3, and then finetunes a smaller model (e.g., RoBERTa) with generated explanations. Our experiments on natural language inference demonstrate effectiveness over strong baselines, increasing accuracy by 17.6% over GPT-3 Babbage and 5.7% over GPT-3 Davinci in e-SNLI. Despite improving classification performance, human evaluation surprisingly reveals that the majority of generated explanations does not adequately justify classification decisions. Additional analyses point to the important role of label-specific cues (e.g., "not know" for the neutral label) in generated explanations.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 57 of its 75 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

57 of 75 references.

References · 57

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  8. 2019Language Models as Knowledge Bases?cited by 1,936
  9. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  10. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  11. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  12. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
38 more
  1. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  2. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  3. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  4. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  5. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  6. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  7. 2022In-context Learning and Induction Headscited by 964
  8. 2019How Can We Know What Language Models Know?cited by 959
  9. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  10. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  11. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  12. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  13. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  14. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 556
  15. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  16. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  17. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  18. 2022Can language models learn from explanations in context?cited by 249
  19. 2018A Simple Method for Commonsense Reasoningcited by 223
  20. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 214
  21. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  22. 2021How Many Data Points is a Prompt Worth?cited by 198
  23. 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
  24. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  25. 2020Measuring Association Between Labels and Free-Text Rationalescited by 160
  26. 2016Generating Visual Explanationscited by 158
  27. 2020WT5?! Training Text-to-Text Models to Explain their Predictionscited by 148
  28. 2022Learning by Distilling Contextcited by 138
  29. 2022Natural Language Descriptions of Deep Visual Featurescited by 137
  30. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  31. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  32. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  33. 2020Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?cited by 95
  34. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  35. 2017Learning with Latent Languagecited by 75
  36. 2018Semi-Supervised Sequence Modeling with Cross-View Trainingcited by 75
  37. 2018Training Classifiers with Natural Language Explanationscited by 58
  38. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 3; 2026: 2.

10 papers.

  1. 2024Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agendacited by 22
  2. 2023Ecologically Valid Explanations for Label Variation in NLIcited by 16
  3. 2023Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learningcited by 4
  4. 2025A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanationscited by 3
  5. 2023FIAT: Fusing learning paradigms with Instruction-Accelerated Tuningcited by 2
  6. 2023What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perceptioncited by 2
  7. 2025Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainabilitycited by 2
  8. 2025Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundariescited by 1
  9. 2026The Overlooked Repetitive Lengthening Form in Sentiment Analysiscited by 1
  10. 2026On the Importance and Evaluation of Narrativity in Natural Language AI Explanationscited by 0