Can we make an LLM agent that shows papers are overclaiming by making a list of implications of a paper's writing that seems far from the evidence given? Can we make an LLM agent that attempts to show these failures empirically? This seems easier than replication.
If you are inspired by this idea, you can reach out to the authors for collaboration or cite it:
@misc{holtzman-llm-provocations-2025,
author = {Holtzman, Ari},
title = {LLM Provocations},
year = {2025},
url = {https://hypogenic.ai/ideahub/idea/l9pQXcaJMv51gl4Rdmpt}
}Please sign in to comment on this idea.
No comments yet. Be the first to share your thoughts!