Reproduce “LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hung-Chun Hsu, Po-Jen Ko, Che-Cheng Wu, Li-Yang Chang, Chuan-Ju Wang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.