Elamur Research⌕
☰
home / papers / 2024 / Timo: Towards Better Temporal Reasoning for Language Models

Timo: Towards Better Temporal Reasoning for Language Models

Paper · 2024 · Zhaochen Su, Jun Zhang, Tong Zhu et al.

Summary

Language models still reason poorly about time. Earlier fixes targeted narrow settings such as time-sensitive question answering, so they carry over badly to other temporal problems. This work looks for one framework that covers many kinds of temporal reasoning. The authors examine 38 subtasks from the Wang & Zhao (2023) benchmark and find that half of them depend on arithmetic and related math skills. They first fine-tune LLaMA2 on math chain-of-thought data from MathInstruct. This helps on math-heavy tasks but barely affects purely temporal ones. To close that gap, they add a self-critic stage. The math-tuned model samples several answers per temporal prompt, and gold labels sort them into correct and incorrect groups. The model then scores the candidates itself to choose strong preference pairs for DPO training. The resulting Timo models (7B and 13B) improve on their base models by 10.0 and 7.6 average accuracy points and lead among models of similar size. General skills stay intact, which is useful wherever reliable reasoning about dates, durations and event order matters.

Key points

  • The 38 temporal subtasks are split evenly into 19 "math-time" tasks (e.g., frequency computation, time-zone or date arithmetic) and 19 "pure-time" tasks (e.g., temporal commonsense, temporal NLI, storytelling).
  • Supervised fine-tuning of LLaMA2-7B on 50k MathInstruct CoT examples raised math-time accuracy from 56.4 to 63.3. Pure-time tasks gained at most 1.9 points, and adding more math data (up to 180k) made both categories slightly worse.
  • In the self-critic temporal optimization step, the math model serves as its own reward model and picks preference pairs through hierarchical scoring. DPO is then trained on those pairs, so no external annotator model is required.
  • Timo-7B and Timo-13B gain +10.0 and +7.6 average accuracy over their counterparts. They set a new state of the art for their size class and improve on every one of the 38 tasks.
  • General abilities were checked with lm-evaluation-harness on MMLU, ARC Challenge, GSM8K, HellaSwag, Winogrande and TruthfulQA. Timo matched or beat the LLaMA, MathLLaMA and Timo-SFT baselines and agreed with the base model on 97% of its correct answers. Code is available at github.com/zhaochen0110/Timo (COLM 2024).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Chinese University of Hong KongHong Kong · China126 works · 14,073 citations🔬Shanghai Artificial Intelligence LaboratoryShanghai · China117 works · 11,281 citations🎓Soochow UniversitySuzhou · China63 works · 4,507 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 works

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3,320 worksReasoning · 1,426 works

Cite

Cite as Zhaochen Su, Jun Zhang, Tong Zhu, Xiaoye Qu, Juntao Li, Min Zhang and Yu Cheng. 2024. Timo: Towards Better Temporal Reasoning for Language Models. arXiv:2406.14192.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2406.14192 · arXiv 2406.14192

@misc{su2024timo,
  title = {{Timo: Towards Better Temporal Reasoning for Language Models}},
  author = {Zhaochen Su, Jun Zhang, Tong Zhu, Xiaoye Qu, Juntao Li, Min Zhang and Yu Cheng},
  year = {2024},
  doi = {10.48550/arxiv.2406.14192},
  eprint = {2406.14192},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2406.14192}
}

References

68 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862, 2022. find
  2. Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, and Jeff Wu. Weak-to-strong generalization: Eliciting strong capabilities with weak supervision, 2023. URL https://arxiv.org/abs/2… ↗
  3. Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie. A survey on evaluation of large language models, 2023.
  4. Wenhu Chen, Xinyi Wang, and William Yang Wang. A dataset for answering time-sensitive questions. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), 2021. URL https://openreview.net/forum?id=9-LSfSU74n-. ↗
  5. Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, and Ting Liu. A survey of chain of thought reasoning: Advances, frontiers and future. arXiv preprint arXiv:2309.15402, 2023. find
  6. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. Think you have solved question answering? try arc, the ai2 reasoning challenge, 2018.
  7. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. Training verifiers to solve math word problems, 2021.
  8. Tri Dao. FlashAttention-2: Faster attention with better parallelism and work partitioning. 2023.
  9. Yann Dubois, Chen Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy S Liang, and Tatsunori B Hashimoto. Alpacafarm: A simulation framework for methods that learn from human feedback. Advances in Neural Information Processing Systems, 36, 2024.
  10. Patrick Fernandes, Daniel Deutsch, Mara Finkelstein, Parker Riley, André FT Martins, Graham Neubig, Ankush Garg, Jonathan H Clark, Markus Freitag, and Orhan Firat. The devil is in the errors: Leveraging large language models for fine-grained machine translation evaluation. arXiv preprint arXiv:2308.…
  11. Leo Gao, Jonathan Tow, Baber Abbasi, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Alain Le Noac’h, Haonan Li, Kyle McDonell, Niklas Muennighoff, Chris Ociepa, Jason Phang, Laria Reynolds, Hailey Schoelkopf, Aviya Skowron, Lintang Sutawika, Eric Tang, Ani… — [doi:10.5281/zenodo](https://doi.org/10.5281/zenodo) find
  12. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. Pal: Program-aided language models, 2023. find
  13. Zhibin Gou, Zhihong Shao, Yeyun Gong, yelong shen, Yujiu Yang, Minlie Huang, Nan Duan, and Weizhu Chen. ToRA: A tool-integrated reasoning agent for mathematical problem solving. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=Ep0TtjVoap… ↗
  14. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding. In International Conference on Learning Representations, 2020.
  15. Jie Huang and Kevin Chen-Chuan Chang. Towards reasoning in large language models: A survey. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Findings of the Association for Computational Linguistics: ACL 2023, pp. 1049–1065, Toronto, Canada, July 2023. Association for Computational Lin…
  16. Rikui Huang, Wei Wei, Xiaoye Qu, Wenfeng Xie, Xianling Mao, and Dangyang Chen. Joint multi-facts reasoning network for complex temporal question answering over knowledge graph, 2024. find
  17. Aditi Jha, Sam Havens, Jeremy Dohmann, Alex Trott, and Jacob Portes. Limit: Less is more for instruction tuning across evaluation paradigms, 2023. find
  18. Jiaming Ji, Tianyi Qiu, Boyuan Chen, Borong Zhang, Hantao Lou, Kaile Wang, Yawen Duan, Zhonghao He, Jiayi Zhou, Zhaowei Zhang, Fanzhi Zeng, Kwan Yee Ng, Juntao Dai, Xuehai Pan, Aidan O’Gara, Yingshan Lei, Hua Xu, Brian Tse, Jie Fu, Stephen McAleer, Yaodong Yang, Yizhou Wang, Song-Chun Zhu, Yike Guo,… — AI Alignment: A Comprehensive Survey
  19. Angeliki Lazaridou, Adhi Kuncoro, Elena Gribovskaya, Devang Agrawal, Adam Liska, Tayfun Terzi, Mai Gimenez, Cyprien de Masson d’Autume, Tomas Kocisky, Sebastian Ruder, et al. Mind the gap: Assessing temporal generalization in neural language models. Advances in Neural Information Processing Systems,… find
  20. Xingxuan Li, Liying Cheng, Qingyu Tan, Hwee Tou Ng, Shafiq Joty, and Lidong Bing. Unlocking temporal question answering for large language models using code execution, 2023. find
  21. Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, and Yejin Choi. Urial: Aligning untuned LLMs with just the ’write’ amount of in-context learning. In The Twelfth International Conference on Learning Representations, 2024. URL https:/… find
  22. Stephanie Lin, Jacob Hilton, and Owain Evans. TruthfulQA: Measuring how models mimic human falsehoods. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio (eds.), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3214–3252, D…
  23. Wei Liu, Weihao Zeng, Keqing He, Yong Jiang, and Junxian He. What makes good data for alignment? a comprehensive study of automatic data selection in instruction tuning. In The Twelfth International Conference on Learning Representations. Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, Jianguang Lou, Ch… — WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
  24. Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang. Wizardcoder: Empowering code large language models with evol-instruct, 2023b. find
  25. Swaroop Mishra, Matthew Finlayson, Pan Lu, Leonard Tang, Sean Welleck, Chitta Baral, Tanmay Rajpurohit, Oyvind Tafjord, Ashish Sabharwal, Peter Clark, and Ashwin Kalyan. LILA: A unified benchmark for mathematical reasoning. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (eds.), Proceedings of th…
  26. Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Peter Clark, Chitta Baral, and Ashwin Kalyan. NumGLUE: A suite of fundamental yet challenging mathematical reasoning tasks. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio (eds.), Proceedings of the 60th Annual Meeting of… find
  27. Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. arXiv preprint arXiv:2308.03188, 2023. find
  28. J Pustejovsky. The timebank corpus. In Proceedings of Corpus Linguistics 2003, pp. 647–656, 2003. find
  29. Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, and Huajun Chen. Reasoning with language model prompting: A survey. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Association for Computat…
  30. Xiaoye Qu, Qiyuan Chen, Wei Wei, Jishuo Sun, and Jianfeng Dong. Alleviating hallucination in large vision-language models with active retrieval augmentation, 2024a. URL https://arxiv.org/abs/2408.00555. — [arXiv:2408.00555](https://arxiv.org/abs/2408.00555) ↗
  31. Xiaoye Qu, Mingyang Song, Wei Wei, Jianfeng Dong, and Yu Cheng. Mitigating multilingual hallucination in large vision-language models, 2024b. URL https://arxiv.org/abs/ 2408.00550. ↗
  32. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. Direct preference optimization: Your language model is secretly a reward model. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. URL https://openreview.net/forum?id=HPu… ↗
  33. Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. {ZeRO-Offload}: Democratizing {Billion-Scale} model training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21), pp. 551–564, 2021.
  34. Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, et al. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950, 2023.
  35. Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, and Xian Li. Branch-solve-merge improves large language model evaluation and generation. arXiv preprint arXiv:2310.15123, 2023. find
  36. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. Winogrande: An adversarial winograd schema challenge at scale. Communications of the ACM, 64(9):99–106, 2021. find
  37. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017. find
  38. Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. Learning to summarize with human feedback. Advances in Neural Information Processing Systems, 33:3008–3021, 2020. find
  39. Zhaochen Su, Zecheng Tang, Xinyan Guan, Lijun Wu, Min Zhang, and Juntao Li. Improving temporal generalization of pre-trained language models with lexical semantic change. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 6380–6393, 2022. find
  40. Zhaochen Su, Juntao Li, Zikang Zhang, Zihan Zhou, and Min Zhang. Efficient continue training of temporal language model with structural information. In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 6315–6329, Singapore, D… find
  41. Zhaochen Su, Juntao Li, Jun Zhang, Tong Zhu, Xiaoye Qu, Pan Zhou, Yan Bowen, Yu Cheng, et al. Living in the moment: Can large language models grasp co-temporal reasoning? arXiv preprint arXiv:2406.09072, 2024. find
  42. Jiankai Sun, Chuanyang Zheng, Enze Xie, Zhengying Liu, Ruihang Chu, Jiaqi Liu, Jiaqi Xu, Mingyu Ding, Hongyang Li, Mengzhe Geng, et al. A survey of reasoning with foundation models: Concepts, methodologies, and outlook. Qingyu Tan, Hwee Tou Ng, and Lidong Bing. Towards benchmarking and improving the… find
  43. Qingyu Tan, Hwee Tou Ng, and Lidong Bing. Towards robust temporal reasoning of large language models via a multi-hop qa dataset and pseudo-instruction tuning. arXiv preprint arXiv:2311.09821, 2023b. find
  44. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. Stanford alpaca: An instruction-following llama model. https://github.com/tatsu-lab/stanford_alpaca, 2023. ↗
  45. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023.
  46. Lewis Tunstall, Edward Beeching, Nathan Lambert, Nazneen Rajani, Kashif Rasul, Younes Belkada, Shengyi Huang, Leandro von Werra, Clémentine Fourrier, Nathan Habib, et al. Zephyr: Direct distillation of lm alignment. arXiv preprint arXiv:2310.16944, 2023. find
  47. Naushad UzZaman, Hector Llorens, James F. Allen, Leon Derczynski, Marc Verhagen, and James Pustejovsky. Tempeval-3: Evaluating events, time expressions, and temporal relations. CoRR, abs/1206.5333, 2012. URL http://arxiv.org/abs/1206.5333. ↗
  48. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. Self-instruct: Aligning language models with self-generated instructions. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Asso… find
  49. Yuqing Wang and Yun Zhao. Tram: Benchmarking temporal reasoning for large language models. arXiv preprint arXiv:2310.00835, 2023. find
  50. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed H Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, 2022.
  51. Peng Xia, Kangyu Zhu, Haoran Li, Hongtu Zhu, Yun Li, Gang Li, Linjun Zhang, and Huaxiu Yao. Rule: Reliable multimodal rag for factuality in medical vision language models, 2024. URL https://arxiv.org/abs/2407.05131. ↗
  52. Siheng Xiong, Ali Payani, Ramana Kompella, and Faramarz Fekri. Large language models can learn temporal reasoning. arXiv preprint arXiv:2401.06853, 2024. find
  53. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, and Daxin Jiang. Wizardlm: Empowering large language models to follow complex instructions, 2023. find
  54. Chenhan Yuan, Qianqian Xie, Jimin Huang, and Sophia Ananiadou. Back to the future: Towards explainable temporal reasoning with large language models. arXiv preprint arXiv:2310.01074, 2023a. find
  55. Chenhan Yuan, Qianqian Xie, Jimin Huang, and Sophia Ananiadou. Back to the future: Towards explainable temporal reasoning with large language models, 2023b. find
  56. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Sainbayar Sukhbaatar, Jing Xu, and Jason Weston. Self-rewarding language models, 2024. find
  57. Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. Mammoth: Building math generalist models through hybrid instruction tuning. arXiv preprint arXiv:2309.05653, 2023.
  58. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. HellaSwag: Can a machine really finish your sentence? In Anna Korhonen, David Traum, and Lluís Màrquez (eds.), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4791–4800, Florence, Ita… find
  59. Michael Zhang and Eunsol Choi. SituatedQA: Incorporating extra-linguistic contexts into QA. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih (eds.), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7371–7387, Online and Punta Can… find
  60. Bowen Zhao, Zander Brumbaugh, Yizhong Wang, Hannaneh Hajishirzi, and Noah A. Smith. Set the clock: Temporal alignment of pretrained language models, 2024. find
  61. Jinman Zhao and Xueyan Zhang. Exploring the limitations of large language models in compositional relation reasoning, 2024. URL https://arxiv.org/abs/2403.02615. — [arXiv:2403.02615](https://arxiv.org/abs/2403.02615) ↗
  62. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, et al. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023.
  63. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. Judging LLM-as-a-judge with MT-bench and chatbot arena. In Thirty-seventh Conference on Neural Information Processing Syste…
  64. Ben Zhou, Daniel Khashabi, Qiang Ning, and Dan Roth. “going on a vacation” takes longer than “going for a walk”: A study of temporal commonsense understanding. In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan (eds.), Proceedings of the 2019 Conference on Empirical Methods in Natural Language… find
  65. Yucheng Zhou, Xiubo Geng, Tao Shen, Guodong Long, and Daxin Jiang. Eventbert: A pre-trained model for event correlation reasoning. In Proceedings of the ACM Web Conference 2022, pp. 850–859, 2022. find
  66. Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, and Yujiu Yang. Solving math word problems via cooperative reasoning induced language models. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki (eds.), Proceedings of the 61st Annual Meeting of the Associ…
  67. Xinyu Zhu, Cheng Yang, Bei Chen, Siheng Li, Jian-Guang Lou, and Yujiu Yang. Question answering as programming for solving time-sensitive questions. arXiv preprint arXiv:2305.14221, 2023b. find
  68. Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593, 2019. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/su-2024-timo-towards-better-temporal-reasoning/