SG-RAG frames retrieval as subgraph matching to ensure LLMs meet every condition in factual queries and reports large gains over baselines on a new 120k-pair ERQA dataset.
hub
Rq-rag: Learning to refine queries for retrieval augmented generation.arXiv preprint arXiv:2404.00610
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
STORM trains lexical query rewriters via reward-guided beam search that converts retrieval metrics into stepwise token signals, enabling 0.6B-8B models to rival dense retrievers on TREC, BEIR and MIRACL without index changes.
BLAgent achieves over 78% top-1 file-level bug localization accuracy on SWE-bench-Lite with open-source models and over 86% with closed-source models while being over 18x cheaper than the strongest baseline.
Attribution graphs reveal that RAG failures arise from shallow fragmented evidence flow in LLMs, enabling topology-based detection and targeted interventions that reinforce question-guided routing.
ReSearch trains LLMs via RL to integrate search operations into reasoning steps, achieving strong generalization across benchmarks and eliciting reflection and self-correction without supervised reasoning data.
A full-paper multimodal knowledge-graph pipeline with a GRPO-trained 4B extractor and tri-source agent CLI reports improved multi-hop scientific reasoning, alongside a released one-million-paper knowledge graph.
SRT framework improves multi-turn dialogue F1 by 4.7% and cuts end-to-end latency by 14.7% via dependency construction, capability initialization, and reasoning improvement with recall tokens.
TrajRAG uses a topological-polar trajectory representation and hierarchical retrieval to accumulate and reuse geometric-semantic navigation experiences, improving zero-shot ObjectNav on MP3D and HM3D benchmarks.
QPP methods can select query variants that boost end-to-end RAG quality over the original query, though retrieval-optimized variants often fail to produce the best generated answers, revealing a utility gap.
Coverage-based retrieval metrics strongly correlate with nugget coverage in RAG outputs at topic and system level, supporting retrieval metrics as proxies for RAG performance when objectives align.
ARK fine-tunes retrievers for answer alignment using KG-augmented curriculum contrastive learning on answer-sufficient positives and progressive hard negatives, reporting 14.5% gains on long-context benchmarks.
RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.
A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.
Replication finds Java security API misuse persists in current LLMs but is reduced by external knowledge in a model-dependent manner.
LightRAG builds graph structures into RAG indexing and retrieval with dual-level search and incremental updates to improve accuracy and speed.
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.
citing papers explorer
-
Structure Guided Retrieval-Augmented Generation for Factual Queries
SG-RAG frames retrieval as subgraph matching to ensure LLMs meet every condition in factual queries and reports large gains over baselines on a new 120k-pair ERQA dataset.
-
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
STORM trains lexical query rewriters via reward-guided beam search that converts retrieval metrics into stepwise token signals, enabling 0.6B-8B models to rival dense retrievers on TREC, BEIR and MIRACL without index changes.
-
BLAgent: Agentic RAG for File-Level Bug Localization
BLAgent achieves over 78% top-1 file-level bug localization accuracy on SWE-bench-Lite with open-source models and over 86% with closed-source models while being over 18x cheaper than the strongest baseline.
-
Why Retrieval-Augmented Generation Fails: A Graph Perspective
Attribution graphs reveal that RAG failures arise from shallow fragmented evidence flow in LLMs, enabling topology-based detection and targeted interventions that reinforce question-guided routing.
-
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
ReSearch trains LLMs via RL to integrate search operations into reasoning steps, achieving strong generalization across benchmarks and eliciting reflection and self-correction without supervised reasoning data.
-
Agents-K1: Towards Agent-native Knowledge Orchestration
A full-paper multimodal knowledge-graph pipeline with a GRPO-trained 4B extractor and tri-source agent CLI reports improved multi-hop scientific reasoning, alongside a released one-million-paper knowledge graph.
-
Improving Multi-turn Dialogue Consistency with Self-Recall Thinking
SRT framework improves multi-turn dialogue F1 by 4.7% and cuts end-to-end latency by 14.7% via dependency construction, capability initialization, and reasoning improvement with recall tokens.
-
TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation
TrajRAG uses a topological-polar trajectory representation and hierarchical retrieval to accumulate and reuse geometric-semantic navigation experiences, improving zero-shot ObjectNav on MP3D and HM3D benchmarks.
-
Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines
QPP methods can select query variants that boost end-to-end RAG quality over the original query, though retrieval-optimized variants often fail to produce the best generated answers, revealing a utility gap.
-
Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage
Coverage-based retrieval metrics strongly correlate with nugget coverage in RAG outputs at topic and system level, supporting retrieval metrics as proxies for RAG performance when objectives align.
-
ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning
ARK fine-tunes retrievers for answer alignment using KG-augmented curriculum contrastive learning on answer-sufficient positives and progressive hard negatives, reporting 14.5% gains on long-context benchmarks.
-
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.
-
Retrieval-Augmented Generation for AI-Generated Content: A Survey
A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.
-
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.
-
R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge
Replication finds Java security API misuse persists in current LLMs but is reduced by external knowledge in a model-dependent manner.
-
LightRAG: Simple and Fast Retrieval-Augmented Generation
LightRAG builds graph structures into RAG indexing and retrieval with dual-level search and incremental updates to improve accuracy and speed.
-
A Survey on Retrieval-Augmented Text Generation for Large Language Models
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.