# When Looks Do Not Lie: Discourse Structure Guided In-Context Learning for Faithful Diagram Generation

arXiv: https://arxiv.org/abs/2601.20476 · HTML: https://mlsanity.com/paper/2601.20476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 92 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 17 of 17)

- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC](https://mlsanity.com/paper/1507.04544/) (2015)
- [Rank-normalization, folding, and localization: An improved widehatR for assessing convergence of MCMC](https://mlsanity.com/paper/1903.08008/) (2019)
- [Unfamiliar Finetuning Examples Control How Language Models Hallucinate](https://mlsanity.com/paper/2403.05612/) (2024)
- [On the Relation between Sensitivity and Accuracy in In-context Learning](https://mlsanity.com/paper/2209.07661/) (2022)
- [AI2D-RST: A multimodal corpus of 1000 primary school science diagrams](https://mlsanity.com/paper/1912.03879/) (2019)
- [In-Context Learning Learns Label Relationships but Is Not Conventional Learning](https://mlsanity.com/paper/2307.12375/) (2023)
- [HALoGEN: Fantastic LLM Hallucinations and Where to Find Them](https://mlsanity.com/paper/2501.08292/) (2025)
- [Can In-context Learning Really Generalize to Out-of-distribution Tasks?](https://mlsanity.com/paper/2410.09695/) (2024)
- [When can in-context learning generalize out of task distribution?](https://mlsanity.com/paper/2506.05574/) (2025)
- [SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement](https://mlsanity.com/paper/2409.19242/) (2024)
- [No Need for Explanations: LLMs can implicitly learn from mistakes in-context](https://mlsanity.com/paper/2502.08550/) (2025)
- [Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning](https://mlsanity.com/paper/2507.22887/) (2025)
- [Discourse Structure in Machine Translation Evaluation](https://mlsanity.com/paper/1710.01504/) (2017)
- [krippendorffsalpha: An R Package for Measuring Agreement Using Krippendorff's Alpha Coefficient](https://mlsanity.com/paper/2103.12170/) (2021)
- [Beyond the Benefits: A Systematic Review of the Harms and Consequences of Generative AI in Computing Education](https://mlsanity.com/paper/2510.04443/) (2025)

## Abstract (arXiv)

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.