LLM agents match or exceed human methodological diversity and produce aligned effect estimates, yet flip final verdicts from 10% to 90% support under a confirmatory prompt while leaving coefficients unchanged.
Base models beat aligned models at random- ness and creativity
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 8roles
background 2representative citing papers
Fine-tuning reorganizes uncertainty in LLMs into more efficient information conveyance, as shown by stronger length-entropy correlations and a tripling of entropy-semantic diversity links after controls.
Activation steering produces synthetic safety-violating data that improves downstream classifiers over prompting on most tested concepts when a harmonic mean of alignment, coherence, and diversity is optimized.
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
Annotation-anchored training reduces semantic diversity collapse in post-trained language models by a factor of six compared to standard supervised fine-tuning while preserving instruction-following and improving with scale.
Proposes a three-phase crystallization model (liquid, nucleation via SFT, settling via RL) for alignment dynamics using random number generation tasks as case study.
IDEAFix is an evaluation framework that varies task attributes and defixation prompts in LLM idea generation, showing task formulation affects performance while simple prompts boost originality but homogenization persists.
citing papers explorer
-
AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively Vulnerable
LLM agents match or exceed human methodological diversity and produce aligned effect estimates, yet flip final verdicts from 10% to 90% support under a confirmatory prompt while leaving coefficients unchanged.
-
Fine-Tuning Improves Information Conveyance in Language Models
Fine-tuning reorganizes uncertainty in LLMs into more efficient information conveyance, as shown by stronger length-entropy correlations and a tripling of entropy-semantic diversity links after controls.
-
Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection
Activation steering produces synthetic safety-violating data that improves downstream classifiers over prompting on most tested concepts when a harmonic mean of alignment, coherence, and diversity is optimized.
-
Annotations Mitigate Post-Training Mode Collapse
Annotation-anchored training reduces semantic diversity collapse in post-trained language models by a factor of six compared to standard supervised fine-tuning while preserving instruction-following and improving with scale.
-
Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization
Proposes a three-phase crystallization model (liquid, nucleation via SFT, settling via RL) for alignment dynamics using random number generation tasks as case study.
-
IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs
IDEAFix is an evaluation framework that varies task attributes and defixation prompts in LLM idea generation, showing task formulation affects performance while simple prompts boost originality but homogenization persists.