5 papers
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…
Harnessing non-adversarial robustness in large language models
Qinghua Zhou, Ellina Aleshina, Andrey Lovyagin +6
The work presents an approach for addressing the challenge of robustness in Large Language Models (LLMs) to alterations and potential errors caused by semantically similar but text…
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.…
When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs
Mikhail Seleznyov, Mikhail Chaichuk, Gleb Ershov +3
Large Language Models (LLMs) are highly sensitive to subtle, non-semantic variations in prompt phrasing and formatting. In this work, we present the first systematic evaluation of…
Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Models
Mikhail Chaichuk, Sushant Gautam, Steven Hicks +1
The generation of realistic medical images from text descriptions has significant potential to address data scarcity challenges in healthcare AI while preserving patient privacy. T…