Conformal Selective Acting (CSA) fills a gap in conformal methods by providing per-round, pathwise-valid selective risk bounds for adaptive RLVR LLM streams under predictable updates and isotonic calibration.
arXiv preprint arXiv:2404.14779 , year =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Federated PEFT on LLMs across healthcare and finance datasets performs close to centralized training and beats isolated local training under non-IID conditions.
MediEval benchmark reveals LLM failures like hallucinated support and truth inversion in medical reasoning, while CoRFu fine-tuning raises macro-F1 by 16.4 points and removes truth inversion errors.
PrinciplismQA benchmark reveals significant gaps in LLMs' clinical ethical reasoning despite high knowledge accuracy.
HuatuoGPT-o1 achieves superior medical complex reasoning by using a verifier to curate reasoning trajectories for fine-tuning and then applying RL with verifier-based rewards.
citing papers explorer
-
MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs
MediEval benchmark reveals LLM failures like hallucinated support and truth inversion in medical reasoning, while CoRFu fine-tuning raises macro-F1 by 16.4 points and removes truth inversion errors.
-
PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment
PrinciplismQA benchmark reveals significant gaps in LLMs' clinical ethical reasoning despite high knowledge accuracy.
-
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
HuatuoGPT-o1 achieves superior medical complex reasoning by using a verifier to curate reasoning trajectories for fine-tuning and then applying RL with verifier-based rewards.