Research
When Looks Do Not Lie: Discourse Structure Guided In-Context Learning for Faithful Diagram Generation
arXiv:2601.20476v2 Announce Type: replace Abstract: GenAI is widespread in educational applications; however, it is known to generate content with intrinsic and extrinsic hallucination. We introduce a
arXiv:2601.20476v2 Announce Type: replace Abstract: GenAI is widespread in educational applications; however, it is known to generate content with intrinsic and extrinsic hallucination. We introduce a novel method for ICL diagram generation based on Rhetorical Structure Theory, which improves diagram faithfulness to its source text context. We find that ICL performance depends on task distribution and models' reasoning ability, with higher reasoning allowing better quality and performance for an out-of-distribution task. We perform an expert evaluation of 150 generated diagrams and analyze our findings using Bayesian GLMMs. Additionally, we use our evaluation rubric and samples from the data set for automated diagram evaluation, achieving statistically significant agreement with human evaluation.
Related
- Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation
- When Discourse Pressures Conflict: Information Structure in Vision-Language Model Outputs
- TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation
Source: arXiv cs.CL | 2026-08-24