LLMs are applied in a generative pipeline for extracting, normalizing, and interpreting eligibility criteria from securities prospectuses, achieving up to 91% precision in document-level decisions with a conservative bias.
In2023 IEEE International Conference on Big Data (BigData)
11 Pith papers cite this work, alongside 77 external citations. Polarity classification is still indexing.
11
Pith papers citing it
77
external citations · external index
representative citing papers
SASAV introduces the first fully autonomous multi-agent system for scientific data analysis and visualization that operates without external prompting or human-in-the-loop feedback.
Introduces a benchmark for MLLM-based chart data extraction from unlabeled images and a human-centered training framework that reaches SOTA numerical accuracy with a 7B model.
Introduces ontology memory-augmented ASR correction that organizes prior interaction history into retrievable nodes and reports gains over direct correction in 9 of 10 backbone-setting pairs on a new long-context dataset.
Comic-based visual narratives achieve over 90% ensemble success rates on multiple MLLMs, outperforming text and random-image baselines while breaking existing safety methods and evaluators.
MARS-S2L ML model detects methane plumes in multispectral satellite imagery at 78% recall with 8% false positives on unseen sites and has enabled verified permanent mitigation at six persistent emitters including a long-running super-emitter in Algeria.
DUET pre-trains dedicated transformers for click and conversion streams, yielding up to 0.38% NE reduction over baselines in OCVR prediction.
A dueling bandit algorithm with belief-aware upper confidence bound is introduced for efficient, interaction-based selection of LLMs matching user latent preferences.
LLMs can detect usability content in user reviews with F-scores comparable to humans, though performance depends strongly on prompt design.
Adding handwritten Cypher graph tools to an agentic RAG system roughly doubled factual-correctness precision and recall on MoNaCo complex questions and improved fine-grained truthfulness compared with vector-only RAG.
A modular XR platform integrates Whisper, NLLB, AWS Polly, RoBERTa, flan-t5, and MediaPipe to deliver real-time multilingual and International Sign support for education, with benchmarks showing AWS Polly's low latency and EuroLLM's higher BLEU score.
citing papers explorer
-
LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank
LLMs are applied in a generative pipeline for extracting, normalizing, and interpreting eligibility criteria from securities prospectuses, achieving up to 91% precision in document-level decisions with a conservative bias.
-
SASAV: Self-Directed Agent for Scientific Analysis and Visualization
SASAV introduces the first fully autonomous multi-agent system for scientific data analysis and visualization that operates without external prompting or human-in-the-loop feedback.
-
Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework
Introduces a benchmark for MLLM-based chart data extraction from unlabeled images and a human-centered training framework that reaches SOTA numerical accuracy with a 7B model.
-
Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations
Introduces ontology memory-augmented ASR correction that organizes prior interaction history into retrievable nodes and reports gains over direct correction in 9 of 10 backbone-setting pairs on a new long-context dataset.
-
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
Comic-based visual narratives achieve over 90% ensemble success rates on multiple MLLMs, outperforming text and random-image baselines while breaking existing safety methods and evaluators.
-
Artificial intelligence for methane detection: from continuous monitoring to verified mitigation
MARS-S2L ML model detects methane plumes in multispectral satellite imagery at 78% recall with 8% false positives on unseen sites and has enabled verified permanent mitigation at six persistent emitters including a long-running super-emitter in Algeria.
-
DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction
DUET pre-trains dedicated transformers for click and conversion streams, yielding up to 0.38% NE reduction over baselines in OCVR prediction.
-
CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLM
A dueling bandit algorithm with belief-aware upper confidence bound is introduced for efficient, interaction-based selection of LLMs matching user latent preferences.
-
User Reviews as a Source for Usability Requirements: A Precursor Study on Using Large Language Models
LLMs can detect usability content in user reviews with F-scores comparable to humans, though performance depends strongly on prompt design.
-
Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
Adding handwritten Cypher graph tools to an agentic RAG system roughly doubled factual-correctness precision and recall on MoNaCo complex questions and improved fine-grained truthfulness compared with vector-only RAG.
-
AI-Driven Modular Services for Accessible Multilingual Education in Immersive Extended Reality Settings: Integrating Speech Processing, Translation, and Sign Language Rendering
A modular XR platform integrates Whisper, NLLB, AWS Polly, RoBERTa, flan-t5, and MediaPipe to deliver real-time multilingual and International Sign support for education, with benchmarks showing AWS Polly's low latency and EuroLLM's higher BLEU score.