Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
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…
cs.CL2024
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…