Evaluating Large Language Models in Summarizing Developer Chat Conversations: A Linguistic Perspective
Anonymous · Zenodo (CERN European Organization for Nuclear Research) · 2025
This is a replication package that includes: GoldenSet: contains the best summaries by participants for each conversation and the corresponding LLM generated summaries) LinguisticAnalysis_HumanGenerated: linguistic analysis such as speech tags, entities, etc. for summaries created by the Mturk participants (golden set) LinguisticAnalysis_LLMGenerated: linguistic analysis such as speech tags, entities etc. for summaries generated by the large language models