conftrace_

explanation verification

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

black-box representation (1) explanation data (1) reward alignment (1) neuro-symbolic framework (1) large language model (1) neuro-symbolic reasoning (1) trajectory ranking (1) chain-of-thought prompting (1) formal verification (1) inverse reinforcement learning (1)

Papers

Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving EMNLP 2024 CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification EACL 2023 Explanation-Guided Reward Alignment IJCAI 2023