LLMs often prefer compromise alternatives over binary moral options and generate alternatives rated higher than human-authored ones on structural and ethical criteria.
Dailydilemmas: Revealing value preferences of llms with quandaries of daily life
6 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
6
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
unclear 1representative citing papers
Explicit gender cues induce bounded but systematic decision flips in LLMs on value trade-offs, with self-attributions frequently denying gender influence.
MM-MoralBench is a new multimodal benchmark that evaluates over 20 LVLMs on moral judgment, classification, and response tasks, finding pronounced divergence from human consensus and limited benefits from scaling or chain-of-thought reasoning.
A methodology to derive targeted Loss of Control mitigations by backchaining from AI errors on national security benchmarks to specific affordances and permissions.
Positive Alignment is defined as AI systems that support human flourishing pluralistically while staying safe and cooperative, presented as a necessary complement to existing safety-focused alignment research.
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
citing papers explorer
-
Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?
LLMs often prefer compromise alternatives over binary moral options and generate alternatives rated higher than human-authored ones on structural and ethical criteria.
-
Do Gender Cues Affect LLM Value Trade-offs? Evidence from a Controlled Decision Benchmark
Explicit gender cues induce bounded but systematic decision flips in LLMs on value trade-offs, with self-attributions frequently denying gender influence.
-
MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
MM-MoralBench is a new multimodal benchmark that evaluates over 20 LVLMs on moral judgment, classification, and response tasks, finding pronounced divergence from human consensus and limited benefits from scaling or chain-of-thought reasoning.
-
Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security
A methodology to derive targeted Loss of Control mitigations by backchaining from AI errors on national security benchmarks to specific affordances and permissions.
-
Positive Alignment: Artificial Intelligence for Human Flourishing
Positive Alignment is defined as AI systems that support human flourishing pluralistically while staying safe and cooperative, presented as a necessary complement to existing safety-focused alignment research.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.