Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
hub
Vera and Vaughan, Jennifer Wortman , year =
12 Pith papers cite this work, alongside 27 external citations. Polarity classification is still indexing.
12
Pith papers citing it
27
external citations · external index
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4representative citing papers
Persona-driven workflow and interface improve automated and human-AI red-teaming of generative AI by incorporating diverse perspectives into adversarial prompt creation.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
The paper extends KMS-detailed-balance Lindbladian constructions beyond Gibbs states to prepare general stationary states σ=f(H)/Tr[f(H)], including microcanonical window states, with polynomial-time quantum circuit implementations.
Mixed-Initiative Context reconceptualizes interaction context as a dynamic, jointly manageable structure that humans and AI can actively organize according to task needs.
LLM chat systems show large differences in reference quantity and quality, but users rarely click or engage with them.
Multi-turn neural transparency using behavioral vectors and dynamic visualizations improves user anticipation and evaluation of LLM trait expression while reducing overconfidence, per a randomized study with 246 participants.
U-Define improves user control in LLM planning by letting people define hard rules and soft preferences in natural language with matching verification methods, raising usefulness and satisfaction scores.
AVA is a specialized GenAI platform for development policy research that provides verifiable syntheses from World Bank reports and is associated with 2.4-3.9 hours of weekly time savings in a large-scale user evaluation.
The paper introduces a dual-layer AI identification framework that integrates cryptographic, blockchain, and zero-knowledge techniques with governance checkpoints to support lifecycle accountability in digital enterprises.
EduQwen 32B models optimized via RL then SFT set new SOTA on the Cross-Domain Pedagogical Knowledge Benchmark and surpass Gemini-3 Pro.
Empirical study with 12 users identifies common interaction patterns and barriers when using LLMs for 3D scene manipulation in immersive settings and proposes design recommendations.
citing papers explorer
-
Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
Concept-based abductive and contrastive explanations find minimal high-level concepts that causally determine vision model outcomes on individual images or groups sharing a specified behavior.
-
PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
Persona-driven workflow and interface improve automated and human-AI red-teaming of generative AI by incorporating diverse perspectives into adversarial prompt creation.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction
The paper extends KMS-detailed-balance Lindbladian constructions beyond Gibbs states to prepare general stationary states σ=f(H)/Tr[f(H)], including microcanonical window states, with polynomial-time quantum circuit implementations.
-
Mixed-Initiative Context: Structuring and Managing Context for Human-AI Collaboration
Mixed-Initiative Context reconceptualizes interaction context as a dynamic, jointly manageable structure that humans and AI can actively organize according to task needs.
-
Analyzing the Presentation, Content, and Utilization of References in LLM-powered Conversational AI Systems
LLM chat systems show large differences in reference quantity and quality, but users rarely click or engage with them.
-
Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
Multi-turn neural transparency using behavioral vectors and dynamic visualizations improves user anticipation and evaluation of LLM trait expression while reducing overconfidence, per a randomized study with 246 participants.
-
U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
U-Define improves user control in LLM planning by letting people define hard rules and soft preferences in natural language with matching verification methods, raising usefulness and satisfaction scores.
-
Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Research
AVA is a specialized GenAI platform for development policy research that provides verifiable syntheses from World Bank reports and is associated with 2.4-3.9 hours of weekly time savings in a large-scale user evaluation.
-
AI Identification: An Integrated Framework for Sustainable Governance in Digital Enterprises
The paper introduces a dual-layer AI identification framework that integrates cryptographic, blockchain, and zero-knowledge techniques with governance checkpoints to support lifecycle accountability in digital enterprises.
-
Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning
EduQwen 32B models optimized via RL then SFT set new SOTA on the Cross-Domain Pedagogical Knowledge Benchmark and surpass Gemini-3 Pro.
-
Analyzing Multimodal Interaction Strategies for LLM-Assisted Manipulation of 3D Scenes
Empirical study with 12 users identifies common interaction patterns and barriers when using LLMs for 3D scene manipulation in immersive settings and proposes design recommendations.