MV-HNSW is the first native hierarchical graph index for multi-vector data, achieving over 90% recall with up to 14x lower search latency than prior filter-and-refine approaches across seven datasets.
Title resolution pending
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference tokens and strong cross-domain transfer.
NuggetIndex manages atomic nuggets with temporal validity and lifecycle metadata to filter outdated information before ranking, yielding 42% higher nugget recall, 9pp better temporal correctness, and 55% fewer conflicts than passage or unmanaged proposition baselines.
ARHN refines hard-negative training data for dense retrieval by using LLMs to convert answer-containing passages into additional positives and exclude answer-containing passages from the negative set.
Generative retrieval beats dense retrieval and BM25 on the LIMIT dataset but degrades with hard negatives due to identifier ambiguity during decoding.
Empirical comparison across 14 retrievers on the BRIGHT benchmark shows reasoning-specialized models can match strong accuracy with competitive speed while many large LLM bi-encoders add latency for small gains and confidence scores remain poorly calibrated.
EASP adds a Probe-then-Plan step so LLMs ground their search plans in actual retrieval snapshots and inventory, yielding higher recall and business metrics in sub-second production search.
SA²CRQ uses sequential adaptive residual quantization based on path entropy plus anchored curriculum regularization from head items to improve both efficiency and cold-start performance in generative retrieval.
AGREE boosts visual document retrieval by adding local relevance signals from MLLM attention maps to global document labels during retriever training.
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
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.
MetaRAG is only partially reproducible with lower absolute scores than originally reported, gains substantially from reranking, and shows greater robustness than SIM-RAG under extended retrieval features.
citing papers explorer
-
Unified and Efficient Approach for Multi-Vector Similarity Search
MV-HNSW is the first native hierarchical graph index for multi-vector data, achieving over 90% recall with up to 14x lower search latency than prior filter-and-refine approaches across seven datasets.
-
GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference tokens and strong cross-domain transfer.
-
NuggetIndex: Governed Atomic Retrieval for Maintainable RAG
NuggetIndex manages atomic nuggets with temporal validity and lifecycle metadata to filter outdated information before ranking, yielding 42% higher nugget recall, 9pp better temporal correctness, and 55% fewer conflicts than passage or unmanaged proposition baselines.
-
ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense Retrieval
ARHN refines hard-negative training data for dense retrieval by using LLMs to convert answer-containing passages into additional positives and exclude answer-containing passages from the negative set.
-
Generative Retrieval Overcomes Limitations of Dense Retrieval but Struggles with Identifier Ambiguity
Generative retrieval beats dense retrieval and BM25 on the LIMIT dataset but degrades with hard negatives due to identifier ambiguity during decoding.
-
Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead
Empirical comparison across 14 retrievers on the BRIGHT benchmark shows reasoning-specialized models can match strong accuracy with competitive speed while many large LLM bi-encoders add latency for small gains and confidence scores remain poorly calibrated.
-
Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
EASP adds a Probe-then-Plan step so LLMs ground their search plans in actual retrieval snapshots and inventory, yielding higher recall and business metrics in sub-second production search.
-
Towards Efficient and Generalizable Retrieval: Adaptive Semantic Quantization and Residual Knowledge Transfer
SA²CRQ uses sequential adaptive residual quantization based on path entropy plus anchored curriculum regularization from head items to improve both efficiency and cold-start performance in generative retrieval.
-
Attention Grounded Enhancement for Visual Document Retrieval
AGREE boosts visual document retrieval by adding local relevance signals from MLLM attention maps to global document labels during retriever training.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
-
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.
-
A Reproducibility Study of Metacognitive Retrieval-Augmented Generation
MetaRAG is only partially reproducible with lower absolute scores than originally reported, gains substantially from reranking, and shows greater robustness than SIM-RAG under extended retrieval features.