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.
In defense of rag in the era of long-context language models.arXiv preprint arXiv:2409.01666
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
Overcoming the limited context limitations in early-generation LLMs, retrieval-augmented generation (RAG) has been a reliable solution for context-based answer generation in the past. Recently, the emergence of long-context LLMs allows the models to incorporate much longer text sequences, making RAG less attractive. Recent studies show that long-context LLMs significantly outperform RAG in long-context applications. Unlike the existing works favoring the long-context LLM over RAG, we argue that the extremely long context in LLMs suffers from a diminished focus on relevant information and leads to potential degradation in answer quality. This paper revisits the RAG in long-context answer generation. We propose an order-preserve retrieval-augmented generation (OP-RAG) mechanism, which significantly improves the performance of RAG for long-context question-answer applications. With OP-RAG, as the number of retrieved chunks increases, the answer quality initially rises, and then declines, forming an inverted U-shaped curve. There exist sweet points where OP-RAG could achieve higher answer quality with much less tokens than long-context LLM taking the whole context as input. Extensive experiments on public benchmark demonstrate the superiority of our OP-RAG.
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
TIGRAG constructs token co-occurrence graphs for scalable graph-augmented RAG and uses iterative entity-driven retrieval to improve multi-hop QA performance over dense and prior graph methods.
PRAG delivers end-to-end private RAG with 72-74% recall via non-interactive homomorphic approximations, interactive client assistance, and operation-error estimation to preserve ranking quality.
SAGE is a training-free context reduction method that converts attention signals from a small LLM into a differential relevance heatmap to select top units for downstream QA, achieving competitive accuracy at 10% token budget on benchmarks like QuALITY-hard.
Jet-Long is a tuning-free bifocal RoPE method that dynamically sets remote group size from sequence length, recovering the base model within the pretrained window and beating prior zero-shot extenders on RULER, HELMET-RAG, and PG-19 with near-FA2 throughput.
Reproducibility study shows position and context size effects in RAG depend on topic sampling and retrieval quality, proposes calibration for stable trends, and releases code after finding discrepancies with prior industry work.
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
Long-context prompting reached 73.1% correctness versus 65.4% for semantic RAG at 26 times the token cost across 972 answers in an expert-validated manufacturing benchmark.
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.
-
Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs
TIGRAG constructs token co-occurrence graphs for scalable graph-augmented RAG and uses iterative entity-driven retrieval to improve multi-hop QA performance over dense and prior graph methods.
-
PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation
PRAG delivers end-to-end private RAG with 72-74% recall via non-interactive homomorphic approximations, interactive client assistance, and operation-error estimation to preserve ranking quality.
-
SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing
SAGE is a training-free context reduction method that converts attention signals from a small LLM into a differential relevance heatmap to select top units for downstream QA, achieving competitive accuracy at 10% token budget on benchmarks like QuALITY-hard.
-
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
Jet-Long is a tuning-free bifocal RoPE method that dynamically sets remote group size from sequence length, recovering the base model within the pretrained window and beating prior zero-shot extenders on RULER, HELMET-RAG, and PG-19 with near-FA2 throughput.
-
Lost in the Evidence? Reproducing Document Position and Context Size Effects in RAG
Reproducibility study shows position and context size effects in RAG depend on topic sampling and retrieval quality, proposes calibration for stable trends, and releases code after finding discrepancies with prior industry work.
-
LLM-Oriented Information Retrieval: A Denoising-First Perspective
Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.
-
The Token Tax of Epistemic Accuracy: Comparing RAG and Long-Context Architectures for Document-Grounded Generative AI Applications
Long-context prompting reached 73.1% correctness versus 65.4% for semantic RAG at 26 times the token cost across 972 answers in an expert-validated manufacturing benchmark.