ReaLM-Retrieve uses step-level uncertainty to trigger retrievals during reasoning, achieving 10.1% better F1 scores and 47% fewer calls on multi-hop QA benchmarks.
Generalizable multilingual hate speech detection on low resource indian languages using fair selection in federated learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 4representative citing papers
eLLM unifies LLM memory management with virtual tensors and elastic ballooning to CPU memory, reporting 2.32x higher decoding throughput and 3x larger batch sizes for 128K inputs.
Production multi-task e-commerce ranking model uses LLM-generated three-level ordinal relevance labels and a unified value model to balance semantic quality against engagement signals.
Supervised models using embeddings like jina and e5 reach up to 92% accuracy on multilingual hate speech detection, substantially outperforming anomaly detection, while PCA to 64 dimensions preserves most performance in the supervised case.
citing papers explorer
-
When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
ReaLM-Retrieve uses step-level uncertainty to trigger retrievals during reasoning, achieving 10.1% better F1 scores and 47% fewer calls on multi-hop QA benchmarks.
-
Joint Optimization of Relevance and Engagement in Multi-Task Ranking for E-Commerce with Efficient LLM Supervision
Production multi-task e-commerce ranking model uses LLM-generated three-level ordinal relevance labels and a unified value model to balance semantic quality against engagement signals.
-
Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task
Supervised models using embeddings like jina and e5 reach up to 92% accuracy on multilingual hate speech detection, substantially outperforming anomaly detection, while PCA to 64 dimensions preserves most performance in the supervised case.