Experiments on four models and three datasets show SFT increases sensitivity to easy contexts while later stages (DPO, RLVR) can reinforce or reverse those preferences depending on the dataset.
Étude comparative de la distribution florale dans une portion des
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Cluster-based semantic chunking does not outperform fixed-size or recursive chunking for RAG on academic theses, and RAGAs faithfulness shows limited reliability in this setup.
citing papers explorer
-
Emergence of Context Characteristics Sensitivity in Large Language Models
Experiments on four models and three datasets show SFT increases sensitivity to easy contexts while later stages (DPO, RLVR) can reinforce or reverse those preferences depending on the dataset.
-
Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
Cluster-based semantic chunking does not outperform fixed-size or recursive chunking for RAG on academic theses, and RAGAs faithfulness shows limited reliability in this setup.