We are pleased to announce that the following paper, co-authored by Associate Professor Teeradaj Racharak, has been accepted for presentation at the NeurIPS Workshop on Foundations of Reasoning in Language Models (FoRLM 2025). The workshop will take place in San Diego, California, December 6–7, 2025, as part of the Conference on Neural Information Processing Systems (NeurIPS), one of the most prestigious venues in the field of machine learning and artificial intelligence.

Accepted Paper

• Feifei Sun, Ziyi Tong, Houjing Wei, Cheng Peng, Teeradaj Racharak, Minh Le Nguyen, Benchmarking Temporal Reasoning: Can Large Language Models Navigate Time When Stories Refuse to Follow a Straight Line?, In the NeurIPS Workshop on Foundations of Reasoning in Language Models (FoRLM), December 6–7, 2025

This work investigates the temporal reasoning abilities of large language models (LLMs) in non-linear narrative contexts. By systematically benchmarking model performance on stories with complex temporal structures, the study sheds light on the strengths and limitations of LLMs in navigating time when conventional chronological order is disrupted.

Congratulations to the authors on this achievement!