Aethel: A Reproducible Graph-Retrieval Framework for Multi-Hop Financial Diligence

• URL: http://arxiv.org/abs/2607.24826v1
• Date: Mon, 20 Jul 2026 21:47:33 GMT
• Title: Aethel: A Reproducible Graph-Retrieval Framework for Multi-Hop Financial Diligence
• Abstract summary: We present Aethel, a reproducible framework that combines bipartite Personalized graph retrieval with a coreference-aware Bipartite Coreference Teleportation layer.<n>Aethel models corpora as entity-passage graphs and propagates relevance through explicit relational paths to support multi-hop financial diligence.<n>We evaluate retrieval over a 4,123-chunk corpus of financial disclosures and find that graph retrieval outperforms dense retrieval on multi-hop recall.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Secondary private equity transactions require rapid synthesis of fragmented, unstructured financial disclosures, where critical metrics and their entity anchors are distributed across disjoint documents with limited lexical overlap. We present Aethel, a reproducible framework that combines bipartite Personalized PageRank graph retrieval with a coreference-aware Bipartite Coreference Teleportation layer and an orchestrated specialist-agent architecture. Aethel models corpora as entity-passage graphs and propagates relevance through explicit relational paths to support multi-hop financial diligence. We evaluate the retrieval layer on 200-question samples from the MuSiQue and 2WikiMultiHopQA validation sets, comparing sparse lexical, dense bi-encoder, vanilla graph, and coreference-aware graph retrieval. Aethel achieves HR@5 of 100.0% on 2WikiMultiHopQA and 88.5% on MuSiQue, improving coverage over vanilla graph retrieval while trading off top-rank precision. We also evaluate retrieval over a 4,123-chunk corpus of financial disclosures and find that graph retrieval outperforms dense retrieval on multi-hop recall but does not surpass a strong BM25 baseline at open-corpus scale. The results show that graph-based retrieval offers interpretable multi-hop evidence paths and degrades more gracefully than dense retrieval as corpus size grows, while also demonstrating that its advantage depends strongly on corpus scale and entity-index quality. Code and evaluation artifacts are released for reproducibility.

Related papers

• Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion [71.20734649881258]
  Real-world multimodal datasets often suffer from modality incompleteness due to sensor failures, annotation scarcity, or privacy constraints.<n>One effective solution is modality completion, which reconstructs missing features to provide modality-complete graphs for downstream tasks.<n>We propose GRE-MC, a Graph Retrieval-Enhanced Modality Completion framework, to overcome these limitations.
  arXiv  Detail & Related papers  (2026-05-01T13:50:52Z)
• $G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA [53.491241153213565]
  $G2$-Reader is a dual-graph system for multimodal question answering.<n>$G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)<n>On VisDoMBench across five multimodal domains, $G2$-Reader with Qwen3-VL-32B-Instruct reaches 66.21% average accuracy, outperforming strong baselines and a standalone GPT-5 (53.08%)
  arXiv  Detail & Related papers  (2026-01-29T17:52:54Z)
• Graph-Anchored Knowledge Indexing for Retrieval-Augmented Generation [53.42323544075114]
  We propose GraphAnchor, a novel Graph-Anchored Knowledge Indexing approach.<n> Experiments on four multi-hop question answering benchmarks demonstrate the effectiveness of GraphAnchor.
  arXiv  Detail & Related papers  (2026-01-23T05:41:05Z)
• N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs [0.0]
  Multi-hop question answering over hybrid table-text data requires retrieving and reasoning across multiple evidence pieces from large corpora.<n>Standard Retrieval-Augmented Generation (RAG) pipelines process documents as flat ranked lists, causing retrieval noise to obscure reasoning chains.<n>N2N-GQA is the first zeroshot framework for open-domain hybrid table-text QA that constructs dynamic evidence graphs from noisy retrieval outputs.
  arXiv  Detail & Related papers  (2026-01-10T15:55:15Z)
• EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory [0.0]
  We introduce EcphoryRAG, an entity-centric knowledge graph RAG framework.<n>During indexing, EcphoryRAG extracts and stores only core entities with corresponding metadata.<n>For retrieval, the system first extracts cue entities from queries, then performs a scalable multi-hop associative search.
  arXiv  Detail & Related papers  (2025-10-10T03:07:27Z)
• Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval [22.33550491040999]
  RAG grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents.<n>We build two plug-and-play retrievers: StatementGraphRAG and TopicGraphRAG.<n>Our methods outperform naive chunk-based RAG achieving an average relative improvement of 23.1% in retrieval recall and correctness.
  arXiv  Detail & Related papers  (2025-06-09T17:58:35Z)
• Siren Federate: Bridging document, relational, and graph models for exploratory graph analysis [0.6349764856675643]
  Investigative require interactive exploratory analysis on large heterogeneous knowledge graphs.<n>This paper discusses the architecture of Siren Federate, a system that efficiently supports exploratory graph analysis.<n> Experiments show that Siren Federate exhibits low latency and scales well with the amount of data, the number of users, and the number of computing nodes.
  arXiv  Detail & Related papers  (2025-04-10T14:52:03Z)
• Scalable Weibull Graph Attention Autoencoder for Modeling Document Networks [50.42343781348247]
  We develop a graph Poisson factor analysis (GPFA) which provides analytic conditional posteriors to improve the inference accuracy. We also extend GPFA to a multi-stochastic-layer version named graph Poisson gamma belief network (GPGBN) to capture the hierarchical document relationships at multiple semantic levels. Our models can extract high-quality hierarchical latent document representations and achieve promising performance on various graph analytic tasks.
  arXiv  Detail & Related papers  (2024-10-13T02:22:14Z)
• How Does Generative Retrieval Scale to Millions of Passages? [68.98628807288972]
  We conduct the first empirical study of generative retrieval techniques across various corpus scales. We scale generative retrieval to millions of passages with a corpus of 8.8M passages and evaluating model sizes up to 11B parameters. While generative retrieval is competitive with state-of-the-art dual encoders on small corpora, scaling to millions of passages remains an important and unsolved challenge.
  arXiv  Detail & Related papers  (2023-05-19T17:33:38Z)
• BASS: Boosting Abstractive Summarization with Unified Semantic Graph [49.48925904426591]
  BASS is a framework for Boosting Abstractive Summarization based on a unified Semantic graph. A graph-based encoder-decoder model is proposed to improve both the document representation and summary generation process. Empirical results show that the proposed architecture brings substantial improvements for both long-document and multi-document summarization tasks.
  arXiv  Detail & Related papers  (2021-05-25T16:20:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.