# Signals Are Not States: Neuro-Symbolic Safeguards for Culturally Aware Classroom AI

arXiv: https://arxiv.org/abs/2603.22793 · HTML: https://mlsanity.com/paper/2603.22793/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [pyannote.audio: neural building blocks for speaker diarization](https://mlsanity.com/paper/1911.01255/) (2019)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [Evaluating Large Language Models in Analysing Classroom Dialogue](https://mlsanity.com/paper/2402.02380/) (2024)
- [Evaluating Multilingual Long-Context Models for Retrieval and Reasoning](https://mlsanity.com/paper/2409.18006/) (2024)
- [Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks](https://mlsanity.com/paper/2506.02483/) (2025)
- [SymCode: A Neurosymbolic Approach to Mathematical Reasoning via Verifiable Code Generation](https://mlsanity.com/paper/2510.25975/) (2025)

## Abstract (arXiv)

Classroom AI systems increasingly infer high-level educational states such as engagement, confusion, collaboration, participation, and instructional quality from multimodal and linguistic signals. In multicultural and multilingual classrooms, such inferences can translate culturally situated behavior into stereotyped claims: silence may be read as disengagement, gaze aversion as inattention, code-switching as low proficiency, or indirect help-seeking as confusion. We argue that stereotype-aware classroom AI should separate observable evidence from culturally loaded interpretation and should treat unsupported construct-level claims as safety risks. We introduce NSCR, a culturally grounded neuro-symbolic framework that converts video, audio, ASR, lesson artifacts, and contextual metadata into typed facts with uncertainty, provenance, and cultural scope, then composes them through executable reasoning and policy constraints. We define a taxonomy of stereotype-prone classroom inferences and propose a benchmark agenda covering culture-conditioned state inference, evidence-grounded claim verification, multilingual and code-switched reasoning, collaboration analysis, counterfactual cultural robustness, and culture-conditioned red-teaming. We further specify metrics for stereotype leakage, unsupported attribution, cultural calibration gaps, abstention under cultural ambiguity, and evidence faithfulness. The contribution is methodological: a concrete framework and evaluation agenda for mitigating stereotyped reasoning in classroom AI, with education as a high-stakes, culturally variable deployment setting.