← Search

Michele Dolfi

5 accepted papers

2025

Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems

COLING 2025industry

Retrieval Augmented Generation (RAG) systems are a widespread application of Large Language Models (LLMs) in the industry. While many tools exist empowering developers to build their own systems, measuring their performance locally, with datasets reflective of the system’s use cases, is a technologi…

Cited by 2SourcePDFScholar
2025

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

ICCV 2025poster

We introduce SmolDocling, an ultra-compact vision-language model targeting end-to-end document conversion. Our model comprehensively processes entire pages by generating DocTags, a new universal markup format that captures all page elements in their full context with location. Unlike existing approa…

2024

ESG Accountability Made Easy: DocQA at Your Service

AAAI 2024technical

We present Deep Search DocQA. This application enables information extraction from documents via a question-answering conversational assistant. The system integrates several technologies from different AI disciplines consisting of document conversion to machine-readable format (via computer vision),…

2024

INDUS: Effective and Efficient Language Models for Scientific Applications

EMNLP 2024industry

Large language models (LLMs) trained on general domain corpora showed remarkable results on natural language processing (NLP) tasks. However, previous research demonstrated LLMs trained using domain-focused corpora perform better on specialized tasks. Inspired by this insight, we developed INDUS, a…

Cited by 8SourcePDFScholar
2022

FETA: Towards Specializing Foundational Models for Expert Task Applications

NeurIPS 2022accept

Foundational Models (FMs) have demonstrated unprecedented capabilities including zero-shot learning, high fidelity data synthesis, and out of domain generalization. However, the parameter capacity of FMs is still limited, leading to poor out-of-the-box performance of FMs on many expert tasks (e.g. r…

Cited by 15SourcePDFScholar