LLM agents exhibit persistent attack-selection biases as fixed traits independent of success rates, with a bias momentum effect that resists steering and yields no performance gain.
We're Different, We're the Same: Creative Homogeneity Across LLMs
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Frontier LLMs generate creative ideas with excess population-level crowding below human-relative parity across tasks, but targeted generation protocols can reduce it.
Proposes a task taxonomy for functional diversity in LLM outputs, validates it via user study, introduces targeted sampling to boost diversity only where needed, and presents evidence that the diversity-quality tradeoff may be an artifact of task-agnostic measurement.
Multiplex semantic networks assembled from verbal fluency, free association, sentence-chain and narrative tasks capture non-redundant aspects of semantic organization and improve ridge-regression prediction of individual creativity scores by 50 percent when layers are combined.
citing papers explorer
-
CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
LLM agents exhibit persistent attack-selection biases as fixed traits independent of success rates, with a bias momentum effect that resists steering and yields no performance gain.
-
Ex Ante Evaluation of AI-Induced Idea Diversity Collapse
Frontier LLMs generate creative ideas with excess population-level crowding below human-relative parity across tasks, but targeted generation protocols can reduce it.
-
Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework
Proposes a task taxonomy for functional diversity in LLM outputs, validates it via user study, introduces targeted sampling to boost diversity only where needed, and presents evidence that the diversity-quality tradeoff may be an artifact of task-agnostic measurement.
-
Introducing multiplex semantic networks as multifaceted representations of creative associative knowledge across multilingual samples
Multiplex semantic networks assembled from verbal fluency, free association, sentence-chain and narrative tasks capture non-redundant aspects of semantic organization and improve ridge-regression prediction of individual creativity scores by 50 percent when layers are combined.
- Large Language Models Align with the Human Brain during Creative Thinking