Rumour detection in Bangla remains severely under-resourced, with prior work conflating it with fake news classification and lacking domain-stratified analysis of the linguistic properties that distinguish misinformation from authentic content. We introduce MisInfo-11K, a domain-stratified corpus of 11,198 instances spanning seven topical domains, constructed from Bangla fact-checking portals and verified news outlets. Using 14 linguistically motivated markers, we show via chi-square and Kruskal-Wallis analysis that 13 of 14 exhibit significant cross-domain variation, revealing distinct deception strategies (e.g., authority mimicry in political rumours, fear amplification in health rumours). Building on this, we introduce the Marker Signal Void (MSV), a chi-square-weighted scoring framework identifying rumour instances with no net discriminative surface signal, establishing Macro-F1 = 0.9843 as the ceiling achievable by this 14-marker set. Benchmarking three pretrained transformers (BanglaBERT, MuRIL, XLM-RoBERTa) against five traditional models, MuRIL achieves the strongest performance (Macro-F1 0.9800), while a marker-augmented Random Forest reaches 0.9750, surpassing XLM-RoBERTa. The gap between the MSV ceiling and transformer performance quantifies the contribution of contextual semantic representations beyond surface-level linguistic cues.

It remains unclear whether LLM capabil- ity gains translate into measurable student learning. We analyze 137 educational NLP papers (2022–2025) across four sectors— assessment and grammatical error correc- tion, feedback and writing support, content and question generation, and tutoring and dialogue—introducing three metrics: Valid- ity Gap (VG, share of studies not evaluat- ing learning outcomes), Deployment Readi- ness Index (DRI, real-world evaluation ex- tent), and Multilingual Equity Index (MEI, language coverage). We find a high validity gap (VG = 0.927), low deployment readiness (DRI = 0.126), and limited multilingual cov- erage (MEI = 0.126); grammatical error cor- rection shows no learning-improvement evi- dence at all (VG = 1.000). DRI correlates with learning-outcome evaluation (ρ = 0.425, p < 0.001). Our taxonomy and metrics offer the first quantitative audit of educational NLP in the LLM era.

Large language models (LLMs) are widely used for paraphrase generation, making it important to evaluate their ability to produce fair outputs under explicit debiasing instructions, particularly for under-resourced languages such as Bangla. Existing work has focused on paraphrase generation and detection but lacks benchmarks for evaluating instruction-guided debiasing. We introduce BaP-Bench, a bias-aware Bangla paraphrase benchmark constructed using four LLMs to evaluate instruction-guided mitigation of stance/sentiment toward women (as a proxy for gender bias). To enable large-scale evaluation, we employ automatic classifier-based annotation to assess the effectiveness of LLM-generated debiased paraphrases. We further demonstrate the utility of BaP-Bench as a downstream benchmark by evaluating transformer-based models on paraphrase detection under debiasing instructions. Results show that LLMs vary considerably in their ability to follow debiasing instructions while preserving paraphrase quality, and that transformer-based models achieve strong performance on the downstream task. BaP-Bench provides a foundation for studying instruction-guided fairness in Bangla paraphrasing and supports future research on bias-aware paraphrase generation and evaluation.

Agents that communicate back and forth with humans to help them execute non-linguistic tasks are a long sought goal of AI. These agents need to translate between utterances and actionable meaning representations that can be interpreted by task-specific problem solvers in a context-dependent manner. They should also be able to learn such actionable interpretations for new predicates on the fly. We define an agent architecture for this scenario and present a series of experiments in the Blocks World domain that illustrate how our architecture supports language learning and problem solving in this domain.