Shahriyar Zaman Ridoy
Author directory2026
From Language Specifications to Executable Turing Machines: Evaluating LLMs as Computational Machine Designers
Shahriyar Zaman Ridoy | S. M. Muhtasimul Hasan | Azmine Toushik Wasi | Kinga Tshering | Koushik Ahamed Tonmoy | Md Mosaddek Khan
Findings of the Association for Computational Linguistics: EMNLP 2026
Shahriyar Zaman Ridoy | S. M. Muhtasimul Hasan | Azmine Toushik Wasi | Kinga Tshering | Koushik Ahamed Tonmoy | Md Mosaddek Khan
Findings of the Association for Computational Linguistics: EMNLP 2026
Recognizing a formal language does not imply the ability to construct the computation that decides it. We operationalize this distinction as an executable benchmark for language-model reasoning: given a formal-language specification, an LLM must synthesize a deterministic or nondeterministic Turing machine that decides the language. We introduce TMEval, a benchmark of 253 language specifications across 7 structural categories spanning context-free and non-context-free phenomena. Each language includes 600 oracle-labeled membership tests, and every output is evaluated as an executable artifact rather than a textual response. Our pipeline enforces a strict output contract, validates machine construction, executes each buildable machine, and assigns one of four outcomes: static_fail, build_fail, semantic_mismatch, or exact_pass. Across eight LLMs, 2,024 model–language candidates, and up to 1,214,400 behavioral evaluations, only 11.12% exactly pass all tests. More than half fail before execution, over one-third implement the wrong language, and 75 languages remain unsolved by all systems. Failure depends less on the context-free/non-context-free boundary than on the operational structure required to realize the specification. TMEval reveals a substantial gap between formal-language recognition and machine-checked symbolic construction. TMEval is available at https://turing-machineeval.github.io/.
Can LLMs Design Computational Machines? Pushdown Automaton Synthesis as a Test of Structured Computational Reasoning
Syed Mumtahin Mahmud | Nazira Jesmin Lina | Shahriyar Zaman Ridoy | S. M. Muhtasimul Hasan | Md Mosaddek Khan
Findings of the Association for Computational Linguistics: EMNLP 2026
Syed Mumtahin Mahmud | Nazira Jesmin Lina | Shahriyar Zaman Ridoy | S. M. Muhtasimul Hasan | Md Mosaddek Khan
Findings of the Association for Computational Linguistics: EMNLP 2026
Artificial intelligence has long been evaluated by its ability to perform computation and structured reasoning. While recent large language models (LLMs) demonstrate strong capabilities in language generation, code synthesis, and structured problem solving, it remains unclear whether they can construct formal computational mechanisms from high-level specifications. In this work, we investigate whether modern LLMs can synthesize pushdown automata (PDAs) from language descriptions expressed in natural language or mathematical form. Because PDA construction requires explicit reasoning about states, transitions, and stack-based memory, it provides a controlled test of structured symbolic reasoning. We introduce the task of pushdown automaton synthesis and develop an automated evaluation framework that verifies generated PDAs through structural buildability checks and execution-based validation. Using a benchmark of context-free languages with labeled test cases, we evaluate contemporary LLMs and analyze their ability to construct and execute formal computational machines. Our results show that current state-of-the-art LLMs struggle to reliably construct executable PDAs, indicating that synthesizing computational mechanisms requiring coordinated reasoning over state transitions and stack-based memory manipulation remains challenging for present-day models. All code and data are available at: https://github.com/Dip-to/Pushdown-Automaton-Synthesis-Dataset.git
Position: Real-World Clinical NLP Robustness Requires Messy, Multimodal, Longitudinal, Privacy-Preserving Corpora
Azmine Toushik Wasi | Shahriyar Zaman Ridoy
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Azmine Toushik Wasi | Shahriyar Zaman Ridoy
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Real-world healthcare data is inherently complex: noisy, incomplete, heterogeneous, and temporally irregular, making clinically robust AI development difficult. Traditional models, trained on idealized datasets, fail to capture these operational realities, limiting real-world performance. We propose the Messy Clinic paradigm: a dataset and blueprint for building AI systems grounded in authentic clinical complexity. This framework enables seamless multimodal data integration across EHRs, imaging, genomics, and wearables, using privacy-preserving methods such as federated learning, synthetic data, and differential privacy. It provides (1) structured methodologies for longitudinal multimodal management, (2) AI techniques resilient to noise and missing data, and (3) governance mechanisms for consent, accountability, and bias mitigation. By embracing the “Messy Clinic,” healthcare AI can shift from artificial idealism to real-world robustness, accelerating research, enabling personalized care, and aligning AI with the true complexity of clinical practice.
Can LLMs Follow the Pulse of a Crisis? Evaluating Crisis Sentiment in Bangladesh’s July Uprising
Md. Samiul Alim | Mahir Shahriar Tamim | Tanvir Ahmed Khan | Sharjil Khan | Rafia Ferdous Duti | Shahriyar Zaman Ridoy | Mohammad Ali Moni
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Md. Samiul Alim | Mahir Shahriar Tamim | Tanvir Ahmed Khan | Sharjil Khan | Rafia Ferdous Duti | Shahriyar Zaman Ridoy | Mohammad Ali Moni
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
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.
Geo-spatial and Geo-temporal Reasoning in Vision-Language and Large Language Models : A Review
Shahriyar Zaman Ridoy | Azmine Toushik Wasi | Koushik Ahamed Tonmoy | Md Rizwan Parvez
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Shahriyar Zaman Ridoy | Azmine Toushik Wasi | Koushik Ahamed Tonmoy | Md Rizwan Parvez
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Geo-spatial and geo-temporal reasoning require models to determine not only what information is present but also where and when it applies, which is critical for applications such as crisis response, environmental monitoring, and urban planning. This review surveys recent advances in vision–language models (VLMs) and large language models (LLMs) that address geographically and temporally grounded reasoning across tasks including image geolocation, spatiotemporal question answering, language-guided navigation, and Earth observation. We organize the literature through a structured analysis covering task families, input modalities, model architectures, and reasoning paradigms, highlighting how perception, retrieval, tool use, and intermediate reasoning steps contribute to system performance. The survey further synthesizes existing datasets and benchmarks, identifying common evaluation pitfalls such as spatial granularity mismatch, temporal drift, geographic bias, and potential data leakage. Finally, we outline key research challenges and opportunities for developing robust, verifiable, and time-aware geo-spatial AI systems while addressing broader concerns related to fairness, bias, and location privacy.
2025
CAPSTONE: Composable Attribute‐Prompted Scene Translation for Zero‐Shot Vision–Language Reasoning
Md. Ismail Hossain | Shahriyar Zaman Ridoy | Moshiur Farazi | Nabeel Mohammed | Shafin Rahman
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
Md. Ismail Hossain | Shahriyar Zaman Ridoy | Moshiur Farazi | Nabeel Mohammed | Shafin Rahman
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
Interpreting visual scenes with high-level reasoning is essential for many real-world applications, such as autonomous systems andcontent moderation, but training and maintaining Vision–Language Models (VLMs) remains resource-intensive and opaque. In this work, we present CAPSTONE, a lightweight, modular framework designed for industrial settings. Instead of relying on multimodal training or fine-tuning large models, CAPSTONE transforms outputs from off-the-shelf vision models into structured text prompts that can be interpreted by a frozen Large Language Model (LLM). This plug-and-play architecture enables reasoning over visual input without access to raw pixels, dramatically reducing computational cost and complexity. On the POPE dataset, our system, using a 7B LLM, outperforms several fully trained VLMs in zero-shot evaluations, while on the VSR benchmark, the 4B model achieves competitive results, together demonstrating strong generalization without retraining. CAPSTONE offers a scalable and interpretable alternative for companies looking to integrate visual reasoning capabilities without the burden of full-scale VLM pipelines.
Search