ServiceNow AI Research

RAG

Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA
Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This …
Language Resources and Evaluation Conference,  2026.
Paper Cite
Hierarchical Retrieval at Scale: Bridging Transparency and Efficiency
Hierarchical Retrieval at Scale: Bridging Transparency and Efficiency
Information retrieval is a core component of many intelligent systems as it enables conditioning of outputs on new and large-scale …
Workshop at the International Conference of Machine Learning (ICML),  2026.
Paper Cite Video
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, …
Conference on Empirical Methods in Natural Language Processing (EMNLP),  2025.
Paper Cite
Multi-task retriever fine-tuning for domain-specific and efficient RAG
Multi-task retriever fine-tuning for domain-specific and efficient RAG
Retrieval-Augmented Generation (RAG) has become ubiquitous when deploying Large Language Models (LLMs), as it can address typical …
Knowledge Discovery and Data Mining,  2025.
Paper Cite
Generating a Low-code Complete Workflow via Task Decomposition and RAG
Generating a Low-code Complete Workflow via Task Decomposition and RAG
AI technologies are moving rapidly from research to production. With the popularity of Foundation Models (FMs) that generate text, …
Conference on AI Engineering (CAIN),  2025.
Paper Cite
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
In-context learning (ICL) approaches typically leverage prompting to condition decoder-only language model generation on reference …
Conference on Empirical Methods in Natural Language Processing (EMNLP),  2024.
Paper Cite Code
Reducing hallucination in structured outputs via Retrieval-Augmented Generation
Reducing hallucination in structured outputs via Retrieval-Augmented Generation
A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have …
North American Chapter of the Association for Computational Linguistics (NAACL),  2024.
Paper Cite Video