David Joy, Brian Hu, Christopher Funk, Arslan Basharat, Bill Ray, Alice Leung, Amy Summerville
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In difficult decision-making scenarios, it is common to have conflicting opinions among expert human decision-makers as there may not be a single right answer. Such decisions may be guided by different attributes that can be used to characterize an individual's decision. We introduce a novel dataset for medical triage decision-making, labeled with a set of decisionmaker attributes (DMAs). This dataset consists of 62 scenarios, covering six different DMAs, including ethical principles such as fairness and moral desert. We present a novel software framework for human-aligned decisionmaking by utilizing these DMAs, paving the way for trustworthy AI with better guardrails. Specifically, we demonstrate how large language models (LLMs) can serve as ethical decision-makers, and how their decisions can be aligned to different DMAs using zero-shot prompting. Our experiments focus on different open-source models with varying sizes and training techniques, such as Falcon, Mistral, and Llama 2. Finally, we also introduce a new form of weighted self-consistency that improves the overall quantified performance. Our results provide new research directions in the use of LLMs as alignable decisionmakers. The dataset and open-source software are publicly available at: https://github. com/ITM-Kitware/llm-alignable-dm.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.06435")
get_code_for_paper("2406.06435")
have("2406.06435")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.06435.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.06435)
Connect an agent — have() is free.