---
title: "Temporal Token Matters — paper by Yang et al. (2026)"
description: "The authors examine how models handle this task internally, using a three-stage Identify-Interpret-Verify approach. 40 references."
authors: ["Zhen Yang", "Xinyue Zhang", "Ping Jian", "Chengzhi Li", "Zhongbin Guo", "Jiaping Feng", "Wenpeng Lu"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.123/"
doi: "10.18653/v1/2026.findings-acl.123"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yang-2026-temporal-token-matters-investigating-interpreting/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-temporal-token-matters-investigating-interpreting/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/52/) / Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models

# Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models

**Authors:** [Zhen Yang](https://md.research.elamur.ai/free/en/authors/zhen-yang/), [Xinyue Zhang](https://md.research.elamur.ai/free/en/authors/xinyue-zhang/), [Ping Jian](https://md.research.elamur.ai/free/en/authors/ping-jian/), [Chengzhi Li](https://md.research.elamur.ai/free/en/authors/chengzhi-li/), [Zhongbin Guo](https://md.research.elamur.ai/free/en/authors/zhongbin-guo/), Jiaping Feng and [Wenpeng Lu](https://md.research.elamur.ai/free/en/authors/wenpeng-lu/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.123/) · [PDF](https://aclanthology.org/2026.findings-acl.123.pdf) · [DOI 10.18653/v1/2026.findings-acl.123](https://doi.org/10.18653/v1/2026.findings-acl.123) · [OpenAlex](https://openalex.org/W7166805410)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Large language models often contradict themselves on simple event-ordering questions. Rephrasing "Is A before B?" as "Is A after B?" can produce incoherent answers. The authors examine how models handle this task internally, using a three-stage Identify-Interpret-Verify approach. For a clean testbed, they used GPT-4o to generate short everyday narratives, each containing two events whose order depends only on the context. The data were then manually filtered. With path patching, they find a small set of attention heads in middle-to-upper layers that causally drive the yes/no decision. Some of these heads focus on temporal words such as "before" and "after", while others attend to structural tokens such as "\<s>" and "?". Knocking out these heads hurts performance. Adjusting their attention, including through a new self-adaptive scheme weighted by each head's causal effect and attention pattern, improves both accuracy and consistency without fine-tuning. The study gives a mechanistic account of temporal ordering and a cheap inference-time way to make it more robust.

## Key points
- **Dataset:** 1,200 GPT-4o-generated candidates were reduced to 1,109 items (539 "before", 570 "after"). Items answerable from world knowledge alone were removed.
- **Baselines (accuracy / consistency):**
  - LLaMA2-7B: 60.69% / 48.69%
  - LLaMA3-8B: 90.08% / 67.72%
  - Qwen2-7B: 89.18% / 88.73%
  - Consistency is computed by swapping "before" and "after" and checking that the answer flips.
- **Key heads:** A head counts as "key" if patching it shifts the logits by more than 5%, a threshold taken from Zhang et al. (2024). Such heads are sparse and split into temporal-token and structural-token specialists.
- **Intervention strength:** An ablation over β shows an inverted-U trend. The best result is at β = 0.4 (63.57% accuracy, 50.68% consistency), with a stable range at β = 0.2–0.4 and decline from β ≥ 0.5.
- **Limitations:** The analysis covers only binary, explicit relations and open-weight models (LLaMA, Qwen). MATRES is also used as an existing benchmark.

*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

- [Beijing Institute of Technology](https://md.research.elamur.ai/free/en/universities/beijing-institute-of-technology/) — University, Beijing, China · 43 works · 3,652 citations
- [Qilu University of Technology](https://md.research.elamur.ai/free/en/universities/qilu-university-of-technology/) — University, Jinan, China · 7 works · 3 citations
- [Shandong Academy of Sciences](https://md.research.elamur.ai/free/en/universities/shandong-academy-of-sciences/) — University, Jinan, China · 4 works · 1 citation
- [National Supercomputing Center in Jinan](https://md.research.elamur.ai/free/en/labs/national-supercomputing-center-in-jinan/) — Research institute, Jinan, China · 3 works

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Zhen Yang, Xinyue Zhang, Ping Jian, Chengzhi Li, Zhongbin Guo, Jiaping Feng and Wenpeng Lu. 2026. Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yang2026temporal,
  title = {{Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models}},
  author = {Zhen Yang, Xinyue Zhang, Ping Jian, Chengzhi Li, Zhongbin Guo, Jiaping Feng and Wenpeng Lu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.123},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.123}
}
```

- [← previous Temporal Text Classification with Large Language Models](https://md.research.elamur.ai/free/en/papers/raihan-2026-temporal-text-classification-large-language/)
- [next → TEN: Table Explicitization, Neurosymbolically](https://md.research.elamur.ai/free/en/papers/mehrotra-2026-ten-table-explicitization-neurosymbolically/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/52/)

## References

40 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Omer Antverg and Yonatan Belinkov. 2022. On the pitfalls of analyzing individual neurons in language models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. [find](https://scholar.google.com/scholar?q=Omer+Antverg+and+Yonatan+Belinkov%2E+2022%2E+On+the+pitfalls+of+analyzing+individual+neurons+in+language+models%2E+In+The+Tenth+International+Conference+on+Learning+Representations%2C+ICLR+2022%2C+Virtual+Event)
2. Lukas Berglund, Meg Tong, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, and Owain Evans. 2024. The reversal curse: Llms trained on "a is b" fail to learn "b is a". In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2… [find](https://scholar.google.com/scholar?q=Lukas+Berglund%2C+Meg+Tong%2C+Maximilian+Kaufmann%2C+Mikita+Balesni%2C+Asa+Cooper+Stickland%2C+Tomasz+Korbak%2C+and+Owain+Evans%2E+2024%2E+The+reversal+curse%3A+Llms+trained+on+%22a+is+b%22+fail+to+learn+%22b+is+a%22%2E+In+The+T)
3. Peter F. Brown, John Cocke, Stephen Della Pietra, Vincent J. Della Pietra, Frederick Jelinek, John D. Lafferty, Robert L. Mercer, and Paul S. Roossin. 1990. [A statistical approach to machine translation](https://md.research.elamur.ai/free/en/papers/brown-1990-statistical-approach-machine-translation/). Comput. Linguistics, 16(2):79–85.
4. Omar F. El-Gayar, Mohammad Al-Ramahi, Abdullah Wahbeh, Tareq Nasralah, and Ahmed Elnoshokaty. 2024. A comparative analysis of the interpretability of LDA and LLM for topic modeling: The case of healthcare apps. In 30th Americas Conference on Information Systems: Elevating Life through Digital Social… [find](https://scholar.google.com/scholar?q=Omar+F%2E+El%2DGayar%2C+Mohammad+Al%2DRamahi%2C+Abdullah+Wahbeh%2C+Tareq+Nasralah%2C+and+Ahmed+Elnoshokaty%2E+2024%2E+A+comparative+analysis+of+the+interpretability+of+LDA+and+LLM+for+topic+modeling%3A+The+case+of+health)
5. Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, and 1 others. 2021. A mathematical framework for transformer circuits. Transformer Circuits Thread, 1(1):12. [find](https://scholar.google.com/scholar?q=Nelson+Elhage%2C+Neel+Nanda%2C+Catherine+Olsson%2C+Tom+Henighan%2C+Nicholas+Joseph%2C+Ben+Mann%2C+Amanda+Askell%2C+Yuntao+Bai%2C+Anna+Chen%2C+Tom+Conerly%2C+and+1+others%2E+2021%2E+A+mathematical+framework+for+transformer+ci)
6. Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, and Muhao Chen. 2024a. Getting sick after seeing a doctor? diagnosing and mitigating knowledge conflicts in event temporal reasoning. In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico… [find](https://scholar.google.com/scholar?q=Tianqing+Fang%2C+Zhaowei+Wang%2C+Wenxuan+Zhou%2C+Hongming+Zhang%2C+Yangqiu+Song%2C+and+Muhao+Chen%2E+2024a%2E+Getting+sick+after+seeing+a+doctor%3F+diagnosing+and+mitigating+knowledge+conflicts+in+event+temporal+reas)
7. Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, and Muhao Chen. 2024b. Getting sick after seeing a doctor? diagnosing and mitigating knowledge conflicts in event temporal reasoning. In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico… [find](https://scholar.google.com/scholar?q=Tianqing+Fang%2C+Zhaowei+Wang%2C+Wenxuan+Zhou%2C+Hongming+Zhang%2C+Yangqiu+Song%2C+and+Muhao+Chen%2E+2024b%2E+Getting+sick+after+seeing+a+doctor%3F+diagnosing+and+mitigating+knowledge+conflicts+in+event+temporal+reas)
8. Bahare Fatemi, Mehran Kazemi, Anton Tsitsulin, Karishma Malkan, Jinyeong Yim, John Palowitch, Sungyong Seo, Jonathan Halcrow, and Bryan Perozzi. 2025. Test of time: A benchmark for evaluating llms on temporal reasoning. In The Thirteenth International Conference on Learning Representations, ICLR 202… [find](https://scholar.google.com/scholar?q=Bahare+Fatemi%2C+Mehran+Kazemi%2C+Anton+Tsitsulin%2C+Karishma+Malkan%2C+Jinyeong+Yim%2C+John+Palowitch%2C+Sungyong+Seo%2C+Jonathan+Halcrow%2C+and+Bryan+Perozzi%2E+2025%2E+Test+of+time%3A+A+benchmark+for+evaluating+llms+on+)
9. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
10. Wes Gurnee, Neel Nanda, Matthew Pauly, Katherine Harvey, Dmitrii Troitskii, and Dimitris Bertsimas. 2023. [Finding neurons in a haystack: Case studies with sparse probing](https://md.research.elamur.ai/free/en/papers/gurnee-2023-finding-neurons-haystack-case-studies/).
11. Trans. Mach. Learn. Res., 2023. [find](https://scholar.google.com/scholar?q=Trans%2E+Mach%2E+Learn%2E+Res%2E%2C+2023%2E)
12. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276.
13. Zhanming Jie, Jierui Li, and Wei Lu. 2022. [Learning to reason deductively: Math word problem solving as complex relation extraction](https://md.research.elamur.ai/free/en/papers/jie-2022-learning-reason-deductively-math-word/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022, pages 5…
14. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, Novemb…
15. Tom Lieberum, Matthew Rahtz, János Kramár, Neel Nanda, Geoffrey Irving, Rohin Shah, and Vladimir Mikulik. 2023. [Does circuit analysis interpretability scale? evidence from multiple choice capabilities in chinchilla](https://md.research.elamur.ai/free/en/papers/lieberum-2023-circuit-analysis-interpretability-scale-evidence/). CoRR, abs/2307.09458.
16. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9,… [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+David+Bau%2C+Alex+Andonian%2C+and+Yonatan+Belinkov%2E+2022%2E+Locating+and+editing+factual+associations+in+GPT%2E+In+Advances+in+Neural+Information+Processing+Systems+35%3A+Annual+Conference+on+Neural)
17. Qiang Ning, Hao Wu, and Dan Roth. 2018. A multi-axis annotation scheme for event temporal relations. In ACL. [find](https://scholar.google.com/scholar?q=Qiang+Ning%2C+Hao+Wu%2C+and+Dan+Roth%2E+2018%2E+A+multi%2Daxis+annotation+scheme+for+event+temporal+relations%2E+In+ACL%2E)
18. Wanting Ning, Lishuang Li, Xueyang Qin, Yubo Feng, and Jingyao Tang. 2024. Temporal cognitive tree: A hierarchical modeling approach for event temporal relation extraction. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, pages 855–… [find](https://scholar.google.com/scholar?q=Wanting+Ning%2C+Lishuang+Li%2C+Xueyang+Qin%2C+Yubo+Feng%2C+and+Jingyao+Tang%2E+2024%2E+Temporal+cognitive+tree%3A+A+hierarchical+modeling+approach+for+event+temporal+relation+extraction%2E+In+Findings+of+the+Associat)
19. Yifu Qiu, Zheng Zhao, Yftah Ziser, Anna Korhonen, Edoardo M. Ponti, and Shay B. Cohen. 2023. Are large language models temporally grounded? CoRR, abs/2311.08398. — [arXiv:2311.08398](https://arxiv.org/abs/2311.08398) [find](https://scholar.google.com/scholar?q=Yifu+Qiu%2C+Zheng+Zhao%2C+Yftah+Ziser%2C+Anna+Korhonen%2C+Edoardo+M%2E+Ponti%2C+and+Shay+B%2E+Cohen%2E+2023%2E+Are+large+language+models+temporally+grounded%3F+CoRR%2C+abs%2F2311%2E08398%2E+%E2%80%94+%5BarXiv%3A2311%2E08398%5D%28https%3A%2F%2Farxiv%2Eorg)
20. Daking Rai, Yilun Zhou, Shi Feng, Abulhair Saparov, and Ziyu Yao. 2024. A practical review of mechanistic interpretability for transformer-based language models. CoRR, abs/2407.02646. [find](https://scholar.google.com/scholar?q=Daking+Rai%2C+Yilun+Zhou%2C+Shi+Feng%2C+Abulhair+Saparov%2C+and+Ziyu+Yao%2E+2024%2E+A+practical+review+of+mechanistic+interpretability+for+transformer%2Dbased+language+models%2E+CoRR%2C+abs%2F2407%2E02646%2E)
21. Tilman Räuker, Anson Ho, Stephen Casper, and Dylan Hadfield-Menell. 2023. Toward transparent AI: A survey on interpreting the inner structures of deep neural networks. In 2023 IEEE Conference on Secure and Trustworthy Machine Learning, SaTML 2023, Raleigh, NC, USA, February 8-10, 2023, pages 464– 48… [find](https://scholar.google.com/scholar?q=Tilman+R%C3%A4uker%2C+Anson+Ho%2C+Stephen+Casper%2C+and+Dylan+Hadfield%2DMenell%2E+2023%2E+Toward+transparent+AI%3A+A+survey+on+interpreting+the+inner+structures+of+deep+neural+networks%2E+In+2023+IEEE+Conference+on+Secur)
22. Lee Sharkey, Dan Braun, and Beren Millidge. 2022. Taking features out of superposition with sparse autoencoders. In AI Alignment Forum, volume 6, pages 12–13. [find](https://scholar.google.com/scholar?q=Lee+Sharkey%2C+Dan+Braun%2C+and+Beren+Millidge%2E+2022%2E+Taking+features+out+of+superposition+with+sparse+autoencoders%2E+In+AI+Alignment+Forum%2C+volume+6%2C+pages+12%E2%80%9313%2E)
23. Rishab Sharma, Fuxiang Chen, Fatemeh H. Fard, and David Lo. 2022. An exploratory study on code attention in BERT. In Proceedings of the 30th IEEE/ACM International Conference on Program Comprehension, ICPC 2022, Virtual Event, May 16-17, 2022, pages 437–448. ACM. [find](https://scholar.google.com/scholar?q=Rishab+Sharma%2C+Fuxiang+Chen%2C+Fatemeh+H%2E+Fard%2C+and+David+Lo%2E+2022%2E+An+exploratory+study+on+code+attention+in+BERT%2E+In+Proceedings+of+the+30th+IEEE%2FACM+International+Conference+on+Program+Comprehension%2C)
24. Zhaochen Su, Juntao Li, Jun Zhang, Tong Zhu, Xiaoye Qu, Pan Zhou, Yan Bowen, Yu Cheng, and Min Zhang. 2024. Living in the moment: Can large language models grasp co-temporal reasoning? In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… [find](https://scholar.google.com/scholar?q=Zhaochen+Su%2C+Juntao+Li%2C+Jun+Zhang%2C+Tong+Zhu%2C+Xiaoye+Qu%2C+Pan+Zhou%2C+Yan+Bowen%2C+Yu+Cheng%2C+and+Min+Zhang%2E+2024%2E+Living+in+the+moment%3A+Can+large+language+models+grasp+co%2Dtemporal+reasoning%3F+In+Proceedings+)
25. Aaquib Syed, Can Rager, and Arthur Conmy. 2023. [Attribution patching outperforms automated circuit discovery](https://md.research.elamur.ai/free/en/papers/syed-2023-attribution-patching-outperforms-automated-circuit/). CoRR, abs/2310.10348.
26. Qingyu Tan, Hwee Tou Ng, and Lidong Bing. 2023. Towards benchmarking and improving the temporal reasoning capability of large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 202… [find](https://scholar.google.com/scholar?q=Qingyu+Tan%2C+Hwee+Tou+Ng%2C+and+Lidong+Bing%2E+2023%2E+Towards+benchmarking+and+improving+the+temporal+reasoning+capability+of+large+language+models%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Associat)
27. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton-Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, and 49 others… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
28. Boshi Wang, Sewon Min, Xiang Deng, Jiaming Shen, You Wu, Luke Zettlemoyer, and Huan Sun. 2023a. [Towards understanding chain-of-thought prompting: An empirical study of what matters](https://md.research.elamur.ai/free/en/papers/wang-2023-understanding-chain-thought-prompting-empirical/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), AC…
29. Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. 2023b. Interpretability in the wild: a circuit for indirect object identification in GPT-2 small. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. O… [find](https://scholar.google.com/scholar?q=Kevin+Ro+Wang%2C+Alexandre+Variengien%2C+Arthur+Conmy%2C+Buck+Shlegeris%2C+and+Jacob+Steinhardt%2E+2023b%2E+Interpretability+in+the+wild%3A+a+circuit+for+indirect+object+identification+in+GPT%2D2+small%2E+In+The+Eleven)
30. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837. 12-16, 2024, pages 14495–14508. Association f…
31. Zhen Yang, Ping Jian, and Chengzhi Li. 2025. Option symbol matters: Investigating and mitigating multiple-choice option symbol bias of large language models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language… [find](https://scholar.google.com/scholar?q=Zhen+Yang%2C+Ping+Jian%2C+and+Chengzhi+Li%2E+2025%2E+Option+symbol+matters%3A+Investigating+and+mitigating+multiple%2Dchoice+option+symbol+bias+of+large+language+models%2E+In+Proceedings+of+the+2025+Conference+of+t)
32. Zhongzhi Yu, Zheng Wang, Yonggan Fu, Huihong Shi, Khalid Shaikh, and Yingyan Celine Lin. 2024. Unveiling and harnessing hidden attention sinks: Enhancing large language models without training through attention calibration. In Forty-first International Conference on Machine Learning, ICML 2024, Vien… [find](https://scholar.google.com/scholar?q=Zhongzhi+Yu%2C+Zheng+Wang%2C+Yonggan+Fu%2C+Huihong+Shi%2C+Khalid+Shaikh%2C+and+Yingyan+Celine+Lin%2E+2024%2E+Unveiling+and+harnessing+hidden+attention+sinks%3A+Enhancing+large+language+models+without+training+through)
33. Wei Zhang, Chaoqun Wan, Yonggang Zhang, Yiu-ming Cheung, Xinmei Tian, Xu Shen, and Jieping Ye. 2024. Interpreting and improving large language models in arithmetic calculation. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. [find](https://scholar.google.com/scholar?q=Wei+Zhang%2C+Chaoqun+Wan%2C+Yonggang+Zhang%2C+Yiu%2Dming+Cheung%2C+Xinmei+Tian%2C+Xu+Shen%2C+and+Jieping+Ye%2E+2024%2E+Interpreting+and+improving+large+language+models+in+arithmetic+calculation%2E+In+Forty%2Dfirst+Internat)
34. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. [Llamafactory: Unified efficient fine-tuning of 100+ language models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations),…
35. Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, and Song Han. 2025. [Duoattention: Efficient long-context LLM inference with retrieval and streaming heads](https://md.research.elamur.ai/free/en/papers/xiao-2024-duoattention-efficient-long-context-llm/). In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-…
36. Jingze Zhu, Yongliang Wu, Wenbo Zhu, Jiawang Cao, Yanqiang Zheng, Jiawei Chen, Xu Yang, Bernt Schiele, Jonas Fischer, and Xinting Hu. 2025. Layercake: Token-aware contrastive decoding within large language model layers. arXiv preprint arXiv:2507.04404. — [arXiv:2507.04404](https://arxiv.org/abs/2507.04404) [find](https://scholar.google.com/scholar?q=Jingze+Zhu%2C+Yongliang+Wu%2C+Wenbo+Zhu%2C+Jiawang+Cao%2C+Yanqiang+Zheng%2C+Jiawei+Chen%2C+Xu+Yang%2C+Bernt+Schiele%2C+Jonas+Fischer%2C+and+Xinting+Hu%2E+2025%2E+Layercake%3A+Token%2Daware+contrastive+decoding+within+large+lan)
37. Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2024. Efficient streaming language models with attention sinks. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. [find](https://scholar.google.com/scholar?q=Guangxuan+Xiao%2C+Yuandong+Tian%2C+Beidi+Chen%2C+Song+Han%2C+and+Mike+Lewis%2E+2024%2E+Efficient+streaming+language+models+with+attention+sinks%2E+In+The+Twelfth+International+Conference+on+Learning+Representations)
38. Yaoming Zhu, Sidi Lu, Lei Zheng, Jiaxian Guo, Weinan Zhang, Jun Wang, and Yong Yu. 2018. [Texygen: A benchmarking platform for text generation models](https://md.research.elamur.ai/free/en/papers/zhu-2018-texygen-benchmarking-platform-text-generation/). In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08-12, 2018, p…
39. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 43 others. 2024a. Qwen2 technical report. CoRR, abs/2407.106… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)
40. Wanqi Yang, Yanda Li, Meng Fang, and Ling Chen. 2024b. Enhancing temporal sensitivity and reasoning for time-sensitive question answering. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November [find](https://scholar.google.com/scholar?q=Wanqi+Yang%2C+Yanda+Li%2C+Meng+Fang%2C+and+Ling+Chen%2E+2024b%2E+Enhancing+temporal+sensitivity+and+reasoning+for+time%2Dsensitive+question+answering%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A)

*Updated 2 November 2026*