Ensemble Diversity Optimization for Subjective Supervision
arXiv:2607.08493v1 Announce Type: cross Abstract: Subjective NLP tasks often exhibit systematic annotator disagreement, requiring models that represent uncertainty rather than collapse it. We…
Read the full articleYou might also wanna read
Semantic-Based Distributed Learning for Diverse and Discriminative Representations
In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint
Verbalized Sampling: A Training-Free Method to Mitigate Mode Collapse and Improve LLM Output Diversity
Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this
arxiv.org·13d agoVerbalized Sampling: A Training-Free Method to Mitigate Mode Collapse and Improve LLM Output Diversity
Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this
arxiv.org·13d ago
DecompR: A Method for Reducing Weighting Noise in Multi-Stakeholder LLM Alignment
Multi-stakeholder tasks require one output to satisfy users with conflicting preferences. Holistic LLM judges conflate utility estimation an
arxiv.org·1mo ago
EntropyLong: Using Predictive Uncertainty to Improve Long-Context Language Model Training
Training long-context language models to capture long-range dependencies requires specialized data construction. Current approaches, such as
arxiv.org·8mo ago
MMR-GRPO: Diversity-Aware Reward Reweighting Accelerates Mathematical Reasoning Model Training
Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance o
arxiv.org·29d ago
Efficient Training Data Reduction Using High-Fidelity Labels and Human Expertise
Our process starts with a zero- or few-shot initial model (LLM-0), which we provide with a prompt describing the content of interest, e.g.,
research.google·11mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.