Nick Byrd, Ph.D.How can #largeLanguageModels scale up development of and insight from #ethics dilemmas?
Researchers had #LLMs make "50 scenarios and 400 unique test items" and collected responses from humans, #GPT4, and #Claude2.
- harm that was necessary to reduce overall harm deemed worse (and more intentional) than harm that was merely a side effect
- same for evitable harm (vs. inevitable) harm
- no effects of harm that required action (vs. omission)
Procedural Dilemma Generation for Moral Reasoning in Humans and Language Models
Author(s): Fränken, Jan-Philipp; Gandhi, Kanishk; Qiu, Tori; Khawaja, Ayesha; Goodman, Noah; Gerstenberg, Tobias | Abstract: As AI systems like language models are increasingly integrated into decision-making processes affecting people's lives, it's critical to ensure that these systems have sound moral reasoning. To test whether they do, we need to develop systematic evaluations. We provide a framework that uses a language model to translate causal graphs that capture key aspects of moral dilemmas into prompt templates. With this framework, we procedurally generated a large and diverse set of moral dilemmas---the OffTheRails benchmark---consisting of 50 scenarios and 400 unique test items. We collected moral permissibility and intention judgments from human participants for a subset of our items and compared these judgments to those from two language models (GPT-4 and Claude-2) across eight conditions. We find that moral dilemmas in which the harm is a necessary means (as compared to a side effect) resulted in lower permissibility and higher intention ratings for both participants and language models. The same pattern was observed for evitable versus inevitable harmful outcomes. However, there was no clear effect of whether the harm resulted from an agent's action versus from having omitted to act. We discuss limitations of our prompt generation pipeline and opportunities for improving scenarios to increase the strength of experimental effects.
Dagger ☀️
Qiita - 人気の記事
Alessio Pomaro
KINEWS24
Ken Kousen
Mahmoud Az
D4vRAM
gittaca