mlsanityData to 7 Oct 2026

Unsupervised Explanation Generation via Correct Instantiations

arXiv 2211.11160 ↗First posted 21 Nov 2022cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

While large pre-trained language models (PLM) have shown their great skills at solving discriminative tasks, a significant gap remains when compared with humans for explanation-related tasks. Among them, explaining the reason why a statement is wrong (e.g., against commonsense) is incredibly challenging. The major difficulty is finding the conflict point, where the statement contradicts our real world. This paper proposes Neon, a two-phrase, unsupervised explanation generation framework. Neon first generates corrected instantiations of the statement (phase I), then uses them to prompt large PLMs to find the conflict point and complete the explanation (phase II). We conduct extensive experiments on two standard explanation benchmarks, i.e., ComVE and e-SNLI. According to both automatic and human evaluations, Neon outperforms baselines, even for those with human-annotated instantiations. In addition to explaining a negative prediction, we further demonstrate that Neon remains effective when generalizing to different scenarios.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 21 Nov 2022.

Builds on

37 of 49 references.

References · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  7. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  8. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  9. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  10. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  11. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  12. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
25 more
  1. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  2. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  3. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
  4. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  5. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  6. 2016Rationalizing Neural Predictionscited by 281
  7. 2017Why We Need New Evaluation Metrics for NLGcited by 232
  8. 2019Probing Neural Network Comprehension of Natural Language Argumentscited by 212
  9. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  10. 2018Multimodal Explanations: Justifying Decisions and Pointing to the Evidencecited by 179
  11. 2019Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasetscited by 173
  12. 2016Generating Visual Explanationscited by 156
  13. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  14. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  15. 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 105
  16. 2018CGMH: Constrained Sentence Generation by Metropolis-Hastings Samplingcited by 93
  17. 2022Describing Differences between Text Distributions with Natural Languagecited by 54
  18. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  19. 2019Does It Make Sense? And Why? A Pilot Study for Sense Making and Explanationcited by 43
  20. 2020SemEval-2020 Task 4: Commonsense Validation and Explanationcited by 42
  21. 2020On Commonsense Cues in BERT for Solving Commonsense Taskscited by 13
  22. 2021Unsupervised Editing for Counterfactual Storiescited by 8
  23. 2020ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)cited by 2
  24. 2020KaLM at SemEval-2020 Task 4: Knowledge-aware Language Models for Comprehension And Generationcited by 1
  25. 2020BUT-FIT at SemEval-2020 Task 4: Multilingual commonsensecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 2.

5 papers.

  1. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  2. 2023Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledgecited by 32
  3. 2024Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Modelscited by 4
  4. 2026FactGuard: Agentic Video Misinformation Detection via Reinforcement Learningcited by 3
  5. 2026GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planningcited by 0