Publications

You can also find my articles on my Google Scholar profile.
† denotes equal contribution; ‡ denotes corresponding author.

202610 papers

Preprint

Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation

Under review

Authors: Syed Rifat Raiyan^†, Md. Tariquzzaman^†, Md Farhan Ishmam^‡, Tenghao Huang.

arXiv PDF Code/Data Website

@article{raiyan2026can,
  title={Can {LLMs} Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation},
  author={Raiyan, Syed Rifat and Tariquzzaman, Md. and Ishmam, Md Farhan and Huang, Tenghao},
  journal={arXiv preprint arXiv:2610.21468},
  year={2026}
}

IEEE

S. R. Raiyan, M. Tariquzzaman, M. F. Ishmam and T. Huang, "Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation," arXiv preprint arXiv:2610.21468, 2026.

Preprint

Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery

Under review

Authors: Syed Rifat Raiyan, Mohsinul Kabir, Hasan Mahmud, Md Kamrul Hasan, Sophia Ananiadou.

arXiv PDF Code/Data

@article{raiyan2026artificial,
  title={Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery},
  author={Raiyan, Syed Rifat and Kabir, Mohsinul and Mahmud, Hasan and Hasan, Md Kamrul and Ananiadou, Sophia},
  journal={arXiv preprint arXiv:2606.08728},
  year={2026}
}

IEEE

S. R. Raiyan, M. Kabir, H. Mahmud, M. K. Hasan and S. Ananiadou, "Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery," arXiv preprint arXiv:2606.08728, 2026.

Preprint

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models

Under review

Authors: Oshayer Siddique^†, J. M Areeb Uzair Alam^†, Md Jobayer Rahman Rafy^†, Syed Rifat Raiyan^†, Hasan Mahmud, Md Kamrul Hasan.

arXiv PDF Code/Data

@article{siddique2026statistically,
  title={Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models},
  author={Siddique, Oshayer and Alam, J. M Areeb Uzair and Rafy, Md Jobayer Rahman and Raiyan, Syed Rifat and Mahmud, Hasan and Hasan, Md Kamrul},
  journal={arXiv preprint arXiv:2607.19364},
  year={2026}
}

IEEE

O. Siddique, J. M. A. U. Alam, M. J. R. Rafy, S. R. Raiyan, H. Mahmud and M. K. Hasan, "Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models," arXiv preprint arXiv:2607.19364, 2026.

IJCNLP-AACL 2026Main

LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution

Accepted to 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 (IJCNLP-AACL 2026), 2026

Oral Presentation;99.6th Percentile in ARR May 2026 (Top 62 / 17,087 submissions)

Authors: Adib Sakhawat^†, Syed Rifat Raiyan^†, Tahsin Islam, Takia Farhin, Hasan Mahmud, Md Kamrul Hasan.

arXiv PDF Code/Data Website

@article{sakhawat2026llmideoplasticity,
  title={{LLM}-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of {LLMs} as a Context-Conditioned Distribution},
  author={Sakhawat, Adib and Raiyan, Syed Rifat and Islam, Tahsin and Farhin, Takia and Mahmud, Hasan and Hasan, Md Kamrul},
  journal={arXiv preprint arXiv:2606.28335},
  year={2026}
}

IEEE

A. Sakhawat, S. R. Raiyan, T. Islam, T. Farhin, H. Mahmud and M. K. Hasan, "LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as a Context-Conditioned Distribution," arXiv preprint arXiv:2606.28335, 2026.

Preprint

Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models

Under review

Authors: Syed Rifat Raiyan.

arXiv PDF Code/Data AI Podcast

@article{raiyan2026narrative,
  title={Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models},
  author={Raiyan, Syed Rifat},
  journal={arXiv preprint arXiv:2604.12076},
  year={2026}
}

IEEE

S. R. Raiyan, "Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models," arXiv preprint arXiv:2604.12076, 2026.

Preprint

Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models

Under review

Authors: Md. Abu Bakor Siddique^†, Shahrin Hossain^†, Sadman Ahmed Siam^†, Syed Rifat Raiyan^‡, Hasan Mahmud, Md Kamrul Hasan.

arXiv PDF Code/Data

@article{siddique2026beyond,
  title={Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models},
  author={Siddique, Md. Abu Bakor and Hossain, Shahrin and Siam, Sadman Ahmed and Raiyan, Syed Rifat and Mahmud, Hasan and Hasan, Md Kamrul},
  journal={arXiv preprint arXiv:2604.00890},
  year={2026}
}

IEEE

M. A. B. Siddique, S. Hossain, S. A. Siam, S. R. Raiyan, H. Mahmud and M. K. Hasan, "Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models," arXiv preprint arXiv:2604.00890, 2026.

Preprint

Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification

Under review

Authors: Masnun Nuha Chowdhury^†, Nusrat Jahan Beg^†, Umme Hunny Khan, Syed Rifat Raiyan^‡, Md Kamrul Hasan, Hasan Mahmud.

arXiv PDF Code/Data

@article{chowdhury2026courtroom,
  title={Courtroom-Style Multi-Agent Debate with Progressive {RAG} and Role-Switching for Controversial Claim Verification},
  author={Chowdhury, Masnun Nuha and Beg, Nusrat Jahan and Khan, Umme Hunny and Raiyan, Syed Rifat and Hasan, Md Kamrul and Mahmud, Hasan},
  journal={arXiv preprint arXiv:2603.28488},
  year={2026}
}

IEEE

M. N. Chowdhury, N. J. Beg, U. H. Khan, S. R. Raiyan, M. K. Hasan and H. Mahmud, "Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification," arXiv preprint arXiv:2603.28488, 2026.

IEEE ICLAD 2026

CircuitLM: A Multi-Agent LLM-Aided Design Framework for Generating Circuit Schematics from Natural Language Prompts

Published in 2026 IEEE International Conference on LLM-Aided Design (ICLAD), 2026

Oral Presentation

Authors: Khandakar Shakib Al Hasan, Syed Rifat Raiyan, Hasin Mahtab Alvee, Wahid Sadik.

arXiv PDF Code/Data Slides

@inproceedings{hasan2026circuitlm,
  title={{CircuitLM}: A Multi-Agent {LLM}-Aided Design Framework for Generating Circuit Schematics from Natural Language Prompts},
  author={Hasan, Khandakar Shakib Al and Raiyan, Syed Rifat and Alvee, Hasin Mahtab and Sadik, Wahid},
  booktitle={2026 IEEE International Conference on LLM-Aided Design (ICLAD)},
  year={2026},
  url={https://arxiv.org/abs/2601.04505}
}

IEEE

K. S. A. Hasan, S. R. Raiyan, H. M. Alvee and W. Sadik, "CircuitLM: A Multi-Agent LLM-Aided Design Framework for Generating Circuit Schematics from Natural Language Prompts," 2026 IEEE International Conference on LLM-Aided Design (ICLAD), 2026.

Preprint

Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias

Under review

Authors: Adib Sakhawat, Tahsin Islam, Takia Farhin, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan.

arXiv PDF Code/Data

@article{sakhawat2026politicalalignment,
  title={Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias},
  author={Sakhawat, Adib and Islam, Tahsin and Farhin, Takia and Raiyan, Syed Rifat and Mahmud, Hasan and Hasan, Md Kamrul},
  journal={arXiv preprint arXiv:2601.06194},
  year={2026}
}

IEEE

A. Sakhawat, T. Islam, T. Farhin, S. R. Raiyan, H. Mahmud and M. K. Hasan, "Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias," arXiv preprint arXiv:2601.06194, 2026.

EMNLP 2026Workshop

FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution

Accepted to Proceedings of the 3rd LUHME Workshop at EMNLP 2026, 2026

Poster Presentation

Authors: Syed Rifat Raiyan, Md Farhan Ishmam, Abdullah Al Imran, Mohammad Ali Moni.

arXiv PDF Code/Data Website

@article{raiyan2025frugalprompt,
  title={FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution},
  author={Raiyan, Syed Rifat and Ishmam, Md Farhan and Imran, Abdullah Al and Moni, Mohammad Ali},
  journal={arXiv preprint arXiv:2510.16439},
  year={2025}
}

IEEE

S. R. Raiyan, M. F. Ishmam, A. A. Imran and M. A. Moni, “FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution,” arXiv preprint arXiv:2510.16439, 2025.

20254 papers

NeurIPS 2025Workshop

ADAB: A Culturally-Aligned Automated Response Generation Framework for Islamic App Reviews by Integrating ABSA and Hybrid RAG

Published in 5th Muslims in ML Workshop co-located with NeurIPS 2025, 2025

Poster Presentation

Authors: K. M. Tahlil Mahfuz Faruk, Mushfiqur Rahman Talha, H. M. Kawsar Ahamad, Mohammad Galib Shams, Nabil Mosharraf Hossain, Syed Rifat Raiyan, Md Kamrul Hasan, Hasan Mahmud, Riasat Islam.

OpenReview PDF

@inproceedings{faruk2025adab,
  title={{ADAB}: A Culturally-Aligned Automated Response Generation Framework for Islamic App Reviews by Integrating {ABSA} and Hybrid {RAG}},
  author={Faruk, K. M. Tahlil Mahfuz and Talha, Mushfiqur Rahman and Ahamad, H. M. Kawsar and Shams, Mohammad Galib and Hossain, Nabil Mosharraf and Raiyan, Syed Rifat and Hasan, Md Kamrul and Mahmud, Hasan and Islam, Riasat},
  booktitle={5th Muslims in ML Workshop co-located with NeurIPS 2025},
  year={2025},
  url={https://openreview.net/forum?id=PnWmDdwTXE}
}

IEEE

K. M. T. M. Faruk, M. R. Talha, H. M. K. Ahamad, M. G. Shams, N. M. Hossain, S. R. Raiyan, M. K. Hasan, H. Mahmud and R. Islam, "ADAB: A Culturally-Aligned Automated Response Generation Framework for Islamic App Reviews by Integrating ABSA and Hybrid RAG," 5th Muslims in ML Workshop co-located with NeurIPS 2025, 2025.

IJCNLP-AACL 2025Findings

PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems

Published in Findings of the Association for Computational Linguistics: IJCNLP-AACL 2025, 2025

Authors: Oshayer Siddique^†, J. M Areeb Uzair Alam^†, Md Jobayer Rahman Rafy^†, Syed Rifat Raiyan^†, Hasan Mahmud, Md Kamrul Hasan.

arXiv PDF Code/Data

@article{siddique2025physicseval,
  title={PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems},
  author={Siddique, Oshayer and Alam, JM and Rafy, Md Jobayer Rahman and Raiyan, Syed Rifat and Mahmud, Hasan and Hasan, Md Kamrul},
  journal={arXiv preprint arXiv:2508.00079},
  year={2025}
}

IEEE

O. Siddique, J. M. A. U. Alam, M. J. R. Rafy, S. R. Raiyan, H. Mahmud and M. K. Hasan, “PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems,” arXiv preprint arXiv:2508.00079, 2025.

ACPR 2025

SCReedSolo: A Secure and Robust LSB Image Steganography Framework with Randomized Symmetric Encryption and Reed-Solomon Coding

Published in Proceedings of the 8th Asian Conference on Pattern Recognition (ACPR 2025), 2025

Oral Presentation

Authors: Syed Rifat Raiyan, Md. Hasanul Kabir.

arXiv PDF Code/Data

@article{raiyan2025screedsolo,
  title={SCReedSolo: A Secure and Robust LSB Image Steganography Framework with Randomized Symmetric Encryption and Reed-Solomon Coding},
  author={Raiyan, Syed Rifat and Kabir, Md Hasanul},
  journal={arXiv preprint arXiv:2503.12368},
  year={2025}
}

IEEE

S. R. Raiyan and M. H. Kabir, “SCReedSolo: A Secure and Robust LSB Image Steganography Framework with Randomized Symmetric Encryption and Reed-Solomon Coding,” arXiv preprint arXiv:2503.12368, 2025.

ICCV 2025Workshop

HaSPeR: An Image Repository for Hand Shadow Puppet Recognition

Published in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025

Oral Presentation;Outstanding Presentation

Authors: Syed Rifat Raiyan, Zibran Zarif Amio, Sabbir Ahmed.

arXiv PDF Code/Data Slides Poster Video

@misc{raiyan2024hasper,
  title={HaSPeR: An Image Repository for Hand Shadow Puppet Recognition},
  author={Syed Rifat Raiyan and Zibran Zarif Amio and Sabbir Ahmed},
  year={2024},
  eprint={2408.10360},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

IEEE

S. R. Raiyan, Z. Z. Amio, and S. Ahmed, “HaSPeR: An Image Repository for Hand Shadow Puppet Recognition,” arXiv preprint arXiv:2408.10360, 2024.

20232 papers

ACL 2023Student Research Workshop

Math Word Problem Solving by Generating Linguistic Variants of Problem Statements

Published in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), 2023

Poster Presentation

Authors: Syed Rifat Raiyan, Md. Nafis Faiyaz, Shah Md. Jawad Kabir, Mohsinul Kabir, Hasan Mahmud, Md Kamrul Hasan.

arXiv PDF Code/Data Slides Poster Video

@misc{raiyan2023math,
  title={Math Word Problem Solving by Generating Linguistic Variants of Problem Statements},
  author={Syed Rifat Raiyan and Md. Nafis Faiyaz and Shah Md. Jawad Kabir and Mohsinul Kabir and Hasan Mahmud and Md Kamrul Hasan},
  year={2023},
  eprint={2306.13899},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}

IEEE

S. R. Raiyan, Md. N. Faiyaz, S. Md. J. Kabir, M. Kabir, H. Mahmud, and M. K. Hasan, “Math Word Problem Solving by Generating Linguistic Variants of Problem Statements,” arXiv preprint arXiv:2306.13899, 2023.

ACL 2023Findings

BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews

Published in Findings of the Association for Computational Linguistics: ACL 2023, 2023

Authors: Mohsinul Kabir^†, Obayed Bin Mahfuz^†, Syed Rifat Raiyan^†, Hasan Mahmud, and Md Kamrul Hasan.

arXiv PDF Code/Data Slides Video

@misc{kabir2023banglabook,
  title={BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews},
  author={Mohsinul Kabir and Obayed Bin Mahfuz and Syed Rifat Raiyan and Hasan Mahmud and Md Kamrul Hasan},
  year={2023},
  eprint={2305.06595},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}

IEEE

M. Kabir, O. B. Mahfuz, S. R. Raiyan, H. Mahmud, and M. K. Hasan, “BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews,” arXiv preprint arXiv:2305.06595, 2023.