Q-RAG trains embedders via RL for multi-step retrieval and reports state-of-the-art results on BabiLong and RULER benchmarks for contexts up to 10M tokens.
Longrope2: Near-lossless llm context window scaling.arXiv preprint arXiv:2502.20082
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
LPES uses per-layer scaling factors optimized by a genetic algorithm with Bézier curves to balance attention and improve long-context LLM performance by up to 11.2% on key-value retrieval.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
citing papers explorer
-
Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training
Q-RAG trains embedders via RL for multi-step retrieval and reports state-of-the-art results on BabiLong and RULER benchmarks for contexts up to 10M tokens.
-
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling
LPES uses per-layer scaling factors optimized by a genetic algorithm with Bézier curves to balance attention and improve long-context LLM performance by up to 11.2% on key-value retrieval.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.