phoenixrecruit··on Toward Guarantees for Clinical Reasoning in Vision Language Modelsnice work!I know about your work, similar to this: https://arxiv.org/abs/2601.20055 and https://github.com/DebarghaG/proofofthought
phoenixrecruit··on Verge: Formal Refinement and Guidance Engine for Verifiable LLM Reasoninghow you made sure that your MCS feedback is actually used in next iteration?
phoenixrecruit··on Grammars of Formal UncertaintyGreat breakdown—PCFG-based uncertainty metrics seem like exactly what we need to make LLM-SMT pipelines robust and reliable!