Enhancing LLM Instruction Following: An Evaluation-Driven Multi-Agentic Workflow for Prompt Instructions Optimization

Documenti analoghi

• Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities
  di: Purpura, Alberto, et al.
  Pubblicazione: (2026)
• A Multi-Stage Workflow for the Review of Marketing Content with Reasoning Large Language Models
  di: Purpura, Alberto, et al.
  Pubblicazione: (2025)
• RIFT: Reordered Instruction Following Testbed To Evaluate Instruction Following in Singular Multistep Prompt Structures
  di: Jaffe, Andrew, et al.
  Pubblicazione: (2026)
• EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
  di: Wu, Xiaorui, et al.
  Pubblicazione: (2025)
• AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
  di: Qi, Yunjia, et al.
  Pubblicazione: (2025)