Dr. Post-Training reframes general data as a data-induced regularizer for LLM post-training updates, yielding a family of methods that outperform data-selection baselines on SFT, RLHF, and RLVR tasks.
InProceedings of human lan- guage technology conference and conference on empirical methods in natural language process- ing, pages 193–200
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
ADAPT is an online reweighting framework for LLM training that outperforms offline data selection and mixing methods in cross-benchmark generalization under equal compute.
AutoSpatial improves VLM spatial reasoning for social navigation by combining minimal manual supervision with auto-labeled VQA pairs and hierarchical training, showing gains up to 20.5% in action prediction over baselines.
MM-LIMA uses proposed quality metrics and a trainable selector to pick 200 high-quality multimodal instruction examples and outperforms MiniGPT-4 on evaluations.
A literature survey that taxonomizes hallucination phenomena in LLMs, reviews evaluation benchmarks, and analyzes approaches for their detection, explanation, and mitigation.
citing papers explorer
-
Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
Dr. Post-Training reframes general data as a data-induced regularizer for LLM post-training updates, yielding a family of methods that outperform data-selection baselines on SFT, RLHF, and RLVR tasks.
-
Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
ADAPT is an online reweighting framework for LLM training that outperforms offline data selection and mixing methods in cross-benchmark generalization under equal compute.
-
AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning
AutoSpatial improves VLM spatial reasoning for social navigation by combining minimal manual supervision with auto-labeled VQA pairs and hierarchical training, showing gains up to 20.5% in action prediction over baselines.
-
MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets
MM-LIMA uses proposed quality metrics and a trainable selector to pick 200 high-quality multimodal instruction examples and outperforms MiniGPT-4 on evaluations.
-
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
A literature survey that taxonomizes hallucination phenomena in LLMs, reviews evaluation benchmarks, and analyzes approaches for their detection, explanation, and mitigation.