6 papers
Citation Failure: Definition, Analysis and Efficient Mitigation
Jan Buchmann, Iryna Gurevych
Citations from LLM-based RAG systems are supposed to simplify response verification. However, this goal is undermined in cases of citation failure, where a model generates a helpfu…
HDT: Hierarchical Document Transformer
Haoyu He, Markus Flicke, Jan Buchmann +2
In this paper, we propose the Hierarchical Document Transformer (HDT), a novel sparse Transformer architecture tailored for structured hierarchical documents. Such documents are ex…
Attribute or Abstain: Large Language Models as Long Document Assistants
Jan Buchmann, Xiao Liu, Iryna Gurevych
LLMs can help humans working with long documents, but are known to hallucinate. Attribution can increase trust in LLM responses: The LLM provides evidence that supports its respons…
Document Structure in Long Document Transformers
Jan Buchmann, Max Eichler, Jan-Micha Bodensohn +2
Long documents often exhibit structure with hierarchically organized elements of different functions, such as section headers and paragraphs. Despite the omnipresence of document s…
CARE: Collaborative AI-Assisted Reading Environment
Dennis Zyska, Nils Dycke, Jan Buchmann +2
Recent years have seen impressive progress in AI-assisted writing, yet the developments in AI-assisted reading are lacking. We propose inline commentary as a natural vehicle for AI…
Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Review
Ilia Kuznetsov, Jan Buchmann, Max Eichler +1
Peer review is a key component of the publishing process in most fields of science. The increasing submission rates put a strain on reviewing quality and efficiency, motivating the…