mlsanityData to 7 Oct 2026

Situated Natural Language Explanations

arXiv 2308.14115 ↗First posted 27 Aug 2023cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to generate coherent natural language explanations (NLE). The existing NLE research perspectives do not take the audience into account. An NLE can have high textual quality, but it might not accommodate audiences' needs and preference. To address this limitation, we propose an alternative perspective, textitsituated NLE. On the evaluation side, we set up automated evaluation scores. These scores describe the properties of NLEs in lexical, semantic, and pragmatic categories. On the generation side, we identify three prompt engineering techniques and assess their applicability on the situations. Situated NLE provides a perspective and facilitates further research on the generation and evaluation of explanations.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 47 of its 68 references that are in the map. First posted on arXiv 27 Aug 2023.

Builds on

47 of 68 references.

References · 47

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  5. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  7. 2022Emergent Abilities of Large Language Modelscited by 2,483
  8. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  9. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  10. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  11. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  12. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
35 more
  1. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  2. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  3. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  4. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  5. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  6. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  7. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  8. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  9. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  10. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  11. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  12. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  13. 2020Measuring Association Between Labels and Free-Text Rationalescited by 159
  14. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 159
  15. 2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
  16. 2019What makes a good conversation? How controllable attributes affect human judgmentscited by 140
  17. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  18. 2020Aligning Faithful Interpretations with their Social Attributioncited by 79
  19. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  20. 2019Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanationscited by 71
  21. 2020An Information Bottleneck Approach for Controlling Conciseness in Rationale Extractioncited by 69
  22. 2022Do Large Language Models know what humans know?cited by 60
  23. 2022Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Searchcited by 58
  24. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  25. 2022Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AIcited by 40
  26. 2020Evaluating and Characterizing Human Rationalescited by 36
  27. 2021A Study of Automatic Metrics for the Evaluation of Natural Language Explanationscited by 34
  28. 2021Generate Natural Language Explanations for Recommendationcited by 22
  29. 2022REV: Information-Theoretic Evaluation of Free-Text Rationalescited by 22
  30. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  31. 2022Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Searchcited by 11
  32. 2021Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehensioncited by 10
  33. 2020Sequential Explanations with Mental Model-Based Policiescited by 8
  34. 2023Exploring Lottery Prompts for Pre-trained Language Modelscited by 5
  35. 2018Semi-supervised classification by reaching consensus among modalitiescited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

2 papers.

  1. 2024LLM-Generated Black-box Explanations Can Be Adversarially Helpfulcited by 20
  2. 2026WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classificationcited by 0