ACE achieves 94.95% F1 on patent claim validation by routing high-entropy cases to an LLM with CoPT reasoning, cutting costs 78% versus full LLM use, with the threshold transferring to real USPTO rejections.
URL:https://arxiv.org/ abs/2407.14467
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
RPA-Check is a new multi-stage framework using dimension definition, boolean checklist augmentation, semantic filtering, and LLM-as-judge verification to assess role-playing agents, with tests on a legal training game showing smaller instruction-tuned models can be more consistent than larger ones.
citing papers explorer
-
Adaptive Cost-Efficient Evaluation for Reliable Patent Claim Validation
ACE achieves 94.95% F1 on patent claim validation by routing high-entropy cases to an LLM with CoPT reasoning, cutting costs 78% versus full LLM use, with the threshold transferring to real USPTO rejections.
-
RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents
RPA-Check is a new multi-stage framework using dimension definition, boolean checklist augmentation, semantic filtering, and LLM-as-judge verification to assess role-playing agents, with tests on a legal training game showing smaller instruction-tuned models can be more consistent than larger ones.