Human communication heavily relies on laconism and inferential pragmatics, allowing listeners to successfully reconstruct rich meaning from sparse, telegraphic speech. In contrast, large language models (LLMs) owe much of their stellar performance to expansive input contexts, yet such verbosity inflates monetary costs, carbon footprint, and inference-time latency. This overhead manifests from the redundant low-utility tokens present in typical prompts, as only a fraction of tokens typically carries the majority of the semantic weight. Inspired by the aforementioned cognitive psycholinguistic processes, we address this inefficiency by introducing FrugalPrompt, a novel prompt compression framework for LLMs, which retains only the most semantically significant tokens. Leveraging two state-of-the-art token attribution methods, GlobEnc and DecompX, we assign salience scores to every token in an input sequence, rank them to retain the top-k% tokens, and obtain a sparse frugalized prompt. We establish the theoretical stability of our approach and provide strong empirical results across a suite of four NLP tasks to study the trade-off between the portion of retained tokens and performance. Experimental findings across retention settings reveal asymmetric performance patterns that suggest potential task contamination effects. We posit that our work contributes to a more nuanced understanding of LLM behavior in performance-efficiency trade-offs and delineates the boundary between tasks tolerant of contextual sparsity and those requiring exhaustive context.

Sentiment analysis during political crises is difficult because language, context, and public reaction can change rapidly. This challenge is especially underexplored for low-resource languages such as Bangla. We introduce **UnrestSent200K**, a Bangla crisis sentiment dataset containing approximately 200K Facebook and YouTube comments from the July–August 2024 Bangladesh uprising. The dataset covers five event-aligned phases, ranging from early escalation and internet blackout to regime transition and a later flood crisis. Each comment is linked to its parent post, allowing evaluation both with and without discourse context. All comments are annotated through a fully human process involving 14 native Bangla-speaking annotators and senior validation. The annotation process achieves substantial agreement, with Cohen’s kappa of 0.73, Krippendorff’s alpha of 0.71, and 94.2% blind-audit agreement. We benchmark fine-tuned encoders, prompted LLMs, and LoRA-tuned LLMs. Results show that adding parent-post context consistently improves performance, while temporal shifts across crisis phases cause large performance drops. Strong LLMs perform well, but they still struggle with sarcasm, implicit political references, and meanings that depend on the event phase. UnrestSent200K provides a benchmark for studying context-aware and temporally robust sentiment analysis in low-resource crisis discourse.