EUVIMEDEUVIMED entdecken
Crossref

Measuring the Unmeasurable: Unveiling Latent Cognitive Capabilities of LLM

Cui Danxin, Sihang Jiang, Keyi Wang, Zhiyi Duan, Yanghua Xiao, Bi Yude, Jiaqing Liang, Minggui He, Shimin Tao, Yilun Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (36) · 30485-30493

DOI: 10.1609/aaai.v40i36.40302 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Cui Danxin und 9 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As large language models (LLMs) are increasingly deployed in high-stakes domains such as education, healthcare, and law, accurately evaluating their nuanced reasoning process becomes essential to ensure their safety, reliability, and trustworthiness. However, most existing benchmarks evaluate LLMs at a coarse granularity. Current benchmarks lack a unified framework and rely on single‐task datasets, overlooking the intermediate steps of complex reasoning. This results in redundant overlap across benchmarks, poor generalization to multifaceted real-world tasks, and underutilizes the rich reasoning traces generated by advanced LLMs.

Zitieren

APA

Danxin, C., Jiang, S., Wang, K., Duan, Z., Xiao, Y., Yude, B., Liang, J., He, M., Tao, S., & Liu, Y. (2026). Measuring the Unmeasurable: Unveiling Latent Cognitive Capabilities of LLM. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 30485-30493. https://doi.org/10.1609/aaai.v40i36.40302

Vancouver

Danxin C, Jiang S, Wang K, Duan Z, Xiao Y, Yude B, et al. Measuring the Unmeasurable: Unveiling Latent Cognitive Capabilities of LLM. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(36):30485-30493. doi:10.1609/aaai.v40i36.40302

BibTeX
@article{Danxin2026,
  author = {Danxin, Cui and Jiang, Sihang and Wang, Keyi and Duan, Zhiyi and Xiao, Yanghua and Yude, Bi and Liang, Jiaqing and He, Minggui and Tao, Shimin and Liu, Yilun},
  title = {Measuring the Unmeasurable: Unveiling Latent Cognitive Capabilities of LLM},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {36},
  pages = {30485--30493},
  doi = {10.1609/aaai.v40i36.40302}
}
Kostenlos starten →