SafePyramid is a three-level benchmark showing frontier LLMs identify all violated rules in only 54.0%, 35.3%, and 12.9% of cases on L0, L1, and L2 respectively, indicating in-context policy guardrailing remains difficult.
Mixed citations
Jacobs and Hanna Wallach
Mixed citation behavior. Most common role is background (40%).
10
Pith papers citing it
7
external citations · Crossref
Background
40% of classified citations
citation-role summary
background 4
other 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10representative citing papers
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
An STS case study of MLB's Automated Ball-Strike System reveals that clear rules still require complex sociotechnical translation and calls for practice-based evaluation of automated enforcement systems.
Visual fingerprints represent distributions of linguistic choices extracted from repeated LLM samples to enable direct comparison of behaviors under different generation conditions.
A conceptual framework is introduced that links activist needs to decentralized social network features and is applied to compare Mastodon and Bluesky plus example communities.
A scoping review and empirical analysis produce a six-category taxonomy of factors driving AI non-development and abandonment, showing that practical issues like resource limits and organizational dynamics often outweigh ethical concerns in real decisions.
VB-Score shows three major LLMs have severe failures in medical entity recognition and factual consistency, with 13.8% lower performance on chronic conditions affecting older and minority groups, indicating condition-based algorithmic discrimination.
Synthetic data generation exhibits disparate impact from group-specific approximation, sampling, and estimation errors; group-wise models improve both utility and parity on graphical model methods.
Structured dataset documentation shows little engagement with major reflexivity themes from FAccT literature, leading to a new codebook and extended datasheet questions.
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.
citing papers explorer
-
SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing
SafePyramid is a three-level benchmark showing frontier LLMs identify all violated rules in only 54.0%, 35.3%, and 12.9% of cases on L0, L1, and L2 respectively, indicating in-context policy guardrailing remains difficult.
-
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
-
Inside Baseball: The Automated Ball-Strike System as an Object Lesson in Technological Rule Enforcement
An STS case study of MLB's Automated Ball-Strike System reveals that clear rules still require complex sociotechnical translation and calls for practice-based evaluation of automated enforcement systems.
-
Visual Fingerprints for LLM Generation Comparison
Visual fingerprints represent distributions of linguistic choices extracted from repeated LLM samples to enable direct comparison of behaviors under different generation conditions.
-
The Activist's Guide to the Decentralized Social Universe: A Framework for Exploring How Decentralized Social Networks Can Support Collective Action
A conceptual framework is introduced that links activist needs to decentralized social network features and is applied to compare Mastodon and Bluesky plus example communities.
-
To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems
A scoping review and empirical analysis produce a six-category taxonomy of factors driving AI non-development and abandonment, showing that practical issues like resource limits and organizational dynamics often outweigh ethical concerns in real decisions.
-
Beyond Semantic Similarity: A Component-Wise Evaluation Framework for Medical Question Answering Systems with Health Equity Implications
VB-Score shows three major LLMs have severe failures in medical entity recognition and factual consistency, with 13.8% lower performance on chronic conditions affecting older and minority groups, indicating condition-based algorithmic discrimination.
-
Disparate Impact in Synthetic Data Generation
Synthetic data generation exhibits disparate impact from group-specific approximation, sampling, and estimation errors; group-wise models improve both utility and parity on graphical model methods.
-
Evaluating Structured Documentation as a Tool for Reflexivity in Dataset Development
Structured dataset documentation shows little engagement with major reflexivity themes from FAccT literature, leading to a new codebook and extended datasheet questions.
-
FAccT-Checked: A Narrative Review of Authority Reconfigurations and Retention in AI-Mediated Journalism
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.