Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs
cs.AI
Submitted: 2026-09-15
Updated: 2026-09-15
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Do GANs actually learn the distribution? An empirical study
- Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
- SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
- Modifying Large Language Model Post-Training for Diverse Creative Writing
- Where does output diversity collapse in post-training?
- Diversity in Large Language Models under Supervised Fine-Tuning
- Does Writing with Language Models Reduce Content Diversity?
- How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse
- Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
- The Homogenizing Effect of Large Language Models on Human Expression and Thought
- Variance reduction in output from generative AI
- Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection