Work

RAG as a collapsed NLG pipeline

Year: 2026

Type: conference-paper

Abstract: We thank Ehud Reiter for insightful discussions on the NLG pipeline and LLMs, which helped sharpen the analysis presented here. We thank the anonymous reviewers for their helpful comments, which have improved our paper, and for their encouragement to expand this work in the future.

Source: Aberdeen University Research Archive (Aberdeen University)

Authors: Sivaprasad, Adarsa, Sundararajan, Barkavi, Howcroft, David M.

Institution: University of Aberdeen

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Cancer Research UK

Awards: G4484375687, G6976145177

OpenAlex ID: W7216931428