mlsanityData to 14 Oct 2026

Appropriateness is all you need!

arXiv 2304.14553 ↗First posted 27 Apr 2023cs.AI cs.CL cs.HCcited by 2

Not on the map. Why?

Abstract (arXiv)

The strive to make AI applications "safe" has led to the development of safety-measures as the main or even sole normative requirement of their permissible use. Similar can be attested to the latest version of chatbots, such as chatGPT. In this view, if they are "safe", they are supposed to be permissible to deploy. This approach, which we call "safety-normativity", is rather limited in solving the emerging issues that chatGPT and other chatbots have caused thus far. In answering this limitation, in this paper we argue for limiting chatbots in the range of topics they can chat about according to the normative concept of appropriateness. We argue that rather than looking for "safety" in a chatbot's utterances to determine what they may and may not say, we ought to assess those utterances according to three forms of appropriateness: technical-discursive, social, and moral. We then spell out what requirements for chatbots follow from these forms of appropriateness to avoid the limits of previous accounts: positionality, acceptability, and value alignment (PAVA). With these in mind, we may be able to determine what a chatbot may and may not say. Lastly, one initial suggestion is to use challenge sets, specifically designed for appropriateness, as a validation method.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 19 of its 61 references that are in the map. First posted on arXiv 27 Apr 2023.

Builds on

19 of 61 references.

References · 19

  1. 2021Ethical and social risks of harm from Language Modelscited by 966
  2. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  3. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  4. 2020Recipes for building an open-domain chatbotcited by 593
  5. 2021Carbon Emissions and Large Neural Network Trainingcited by 567
  6. 2022Improving alignment of dialogue agents via targeted human judgementscited by 531
  7. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 403
  8. 2023Larger language models do in-context learning differentlycited by 394
  9. 2016Deep Reinforcement Learning for Dialogue Generationcited by 288
  10. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 182
  11. 2020Recipes for Safety in Open-domain Chatbotscited by 170
  12. 2017Understanding Abuse: A Typology of Abusive Language Detection Subtaskscited by 116
7 more
  1. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 107
  2. 2019Understanding artificial intelligence ethics and safetycited by 68
  3. 2022In conversation with Artificial Intelligence: aligning language models with human valuescited by 62
  4. 2017A Challenge Set Approach to Evaluating Machine Translationcited by 37
  5. 2021User Tampering in Reinforcement Learning Recommender Systemscited by 23
  6. 2022Metaethical Perspectives on 'Benchmarking' AI Ethicscited by 12
  7. 2020Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodologycited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluationcited by 19
  2. 2023Thinking Assistants: LLM-Based Conversational Assistants that Help Users Think By Asking rather than Answeringcited by 4