2 papers
cs.AI2026
Structural Chain-of-Thought: Reasoning with Executable Computational Graphs
Petr Senatorov, Karim Vafin, Elena Tutubalina +1
Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and not always faithful. We int…
cs.AI2026
Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures
Oleg Somov, Mikhail Chaichuk, Gleb Ershov +4
In schema-guided reasoning (SGR) pipelines, LLMs produce explicit intermediate structures -- rubrics, checklists, or verification queries -- before committing to a final decision.…