2026
InstructSum: A Benchmark to Evaluate Instruction-Following Capability of Large Language Models in Summarization
This study introduces a novel benchmark, InstructSum, consisting of 3,309 types of instructions to evaluate the instruction-following capability in the summarization task, and reveals the challenges that LLMs face in this task.
Kosuke Nishida, Kyosuke Nishida, Itsumi Saito
· International Conference on... · 0 citations