Pharos-ESG is a unified framework that converts ESG reports into structured representations using multimodal parsing, contextual narration, and hierarchical labeling. It incorporates a reading‑order model based on layout flow, hierarchy‑aware segmentation guided by table‑of‑contents anchors, and a multimodal aggregation pipeline that turns visual elements into coherent natural language. The framework adds ESG, GRI, and sentiment labels and outperforms existing document parsing systems and general multimodal models, while also releasing Aurora‑ESG, a large‑scale public dataset of ESG reports with detailed layout and semantic annotations.
arXiv:2609.38523v1 Announce Type: cross Abstract: Financial forecasting from earnings conference calls requires models to reason over complex corporate disclosures, market expectations, and subtle co...
arXiv:2610.20335v1 Announce Type: new Abstract: Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction,...
arXiv:2608. 04071v1 Announce Type: new Abstract: Automatically generating professional multimodal reports comprising both textual analysis and visual charts from structured tabular data is a critical challenge in data intelligence.
Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scie...
arXiv:2608. 19526v1 Announce Type: cross Abstract: Stock market analysts and investors face a daily challenge: too much financial news, too little time.
The paper introduces a training‑free, alignment‑free method for corporate intelligence that uses deterministic sparse seed vectors to hash word strings into a fixed high‑dimensional basis. By accumulating these seed vectors across sentence contexts, the authors create corpus‑specific semantic signatures that enable rapid document comparison, issuer fingerprinting, vocabulary shift tracking, and thematic sentence extraction—all on standard CPU hardware. Applied to a multi‑year set of SEC filings, the approach reveals distinct semantic profiles for major corporate events such as Boeing’s 737 MAX crisis, Intel’s supply‑chain disruptions, and Bunge’s acquisition of Viterra, with each profile traceable to its source sentences without any domain‑specific training or LLM inference.
arXiv:2610.09529v1 Announce Type: new Abstract: There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial r...
DocXEval is the first comprehensive framework that adapts existing explainable AI methods and evaluation metrics to multimodal document understanding, covering text, layout, and image modalities. The authors systematically evaluate 13 XAI methods across 3 tasks, 8 datasets, 4 models, and 17 metrics, finding that Occlusion consistently performs best in faithfulness and interpretability. The study also provides meta‑evaluation insights, diagnostic analyses of modality contributions, spatial attribution patterns, and potential dataset biases, offering a benchmark and practical guide for future research.
The paper investigates whether multimodal time‑series forecasting models actually use the semantic content of accompanying text. By systematically perturbing the text—replacing it with empty, constant, shuffled, or cross‑domain sentences—the authors find that mean squared error changes by less than 0.5 % across several architectures, indicating that text does not drive performance gains. They also show that removing a co‑shipped numeric column restores the reported improvements, suggesting that the models rely on other signals rather than textual semantics.
The paper presents the CDSP (context-conditional deliberation signal pipeline), which transforms investment committee meeting transcripts into structured predictive features. CDSP segments transcripts into topical chunks, assigns asset‑class context labels via a large language model, maps financial keywords to a taxonomy, and adds sentiment polarity and mention frequency features. Using these engineered features on 48 monthly meetings, the best model—combining sentence embeddings with CDSP features—achieves 73% accuracy and a 0.73 F1 score, outperforming a simple stock‑choice baseline, though the improvement is not statistically significant.
arXiv:2606. 04231v1 Announce Type: cross Abstract: Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and for answer generation.
arXiv:2609.27784v1 Announce Type: cross Abstract: Semi-structured documents are ubiquitous in scientific reports, financial statements, and technical manuals. Question answering over such documents r...