mlsanityData to 14 Oct 2026

KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations

arXiv 2306.02980 ↗First posted 5 Jun 2023cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs. In this work, we leverage external knowledge bases to significantly improve on an existing adversarial attack for detecting inconsistent NLEs. We apply our attack to high-performing NLE models and show that models with higher NLE quality do not necessarily generate fewer inconsistencies. Moreover, we propose an off-the-shelf mitigation method to alleviate inconsistencies by grounding the model into external background knowledge. Our method decreases the inconsistencies of previous high-performing NLE models as detected by our attack.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

26 of 41 references.

References · 26

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  3. 2019Language Models as Knowledge Bases?cited by 1,936
  4. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  5. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  6. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
  7. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  8. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 380
  9. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  10. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  11. 2018Textual Explanations for Self-Driving Vehiclescited by 226
  12. 2020Measuring Association Between Labels and Free-Text Rationalescited by 160
14 more
  1. 2020WT5?! Training Text-to-Text Models to Explain their Predictionscited by 148
  2. 2018Dialogue Natural Language Inferencecited by 135
  3. 2019Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Trainingcited by 110
  4. 2023Faithfulness Tests for Natural Language Explanationscited by 107
  5. 2020NILE : Natural Language Inference with Faithful Natural Language Explanationscited by 96
  6. 2018Grounding Visual Explanationscited by 93
  7. 2021e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Taskscited by 84
  8. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  9. 2019Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanationscited by 71
  10. 2020Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphscited by 46
  11. 2022Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inferencecited by 40
  12. 2020Fusing Context Into Knowledge Graph for Commonsense Question Answeringcited by 33
  13. 2022Explaining Chest X-ray Pathologies in Natural Languagecited by 27
  14. 2022Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Taskscited by 6

Built on by

Cited by year

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

4 papers.

  1. 2024Do Large Language Models Latently Perform Multi-Hop Reasoning?cited by 169
  2. 2023The Impact of Imperfect XAI on Human-AI Decision-Makingcited by 21
  3. 2023Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionarycited by 4
  4. 2025Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanationscited by 1