Annotations Mitigate Post-Training Mode Collapse
cs.CL
Submitted: 2026-05-11
Updated: 2026-11-03
Terminology
Sources
- Intent Factored Generation: Unleashing the Diversity in Your Language Model
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Language GANs Falling Short
- Plug and Play Language Models: A Simple Approach to Controlled Text Generation
- Hierarchical Neural Story Generation
- Parameterized Synthetic Text Generation with SimpleStories
- The Llama 3 Herd of Models
- Detecting Mode Collapse in Language Models via Narration
- Training Compute-Optimal Large Language Models
- The Curious Case of Neural Text Degeneration
- Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Understanding the Effects of RLHF on LLM Generalisation and Diversity
- Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Preserving Diversity in Supervised Fine-Tuning of Large Language Models
- 2 OLMo 2 Furious
- Does Writing with Language Models Reduce Content Diversity?
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data