Metraipolis › archive › dc_54bcf9002dfd

Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning — arXiv:2608.26166

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26166
License (as archived): CC0-1.0
Archived: 2026-10-17T14:24:24.246Z
SHA-256 of the archived text: 77b91e15db20f4964273d13c101d7ad36b40b55eeb1dd02bc3c8e409fc257828
Stable URL of this page: https://metraipolis.com/documento/dc_54bcf9002dfd

How to cite

Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning — arXiv:2608.26166 — arXiv (en), https://arxiv.org/abs/2608.26166 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54bcf9002dfd (Metraipolis archive dc_54bcf9002dfd, sha256 77b91e15db20f4964273d13c101d7ad36b40b55eeb1dd02bc3c8e409fc257828)

BibTeX

@misc{dc54bcf9002dfd,
  title = {Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning — arXiv:2608.26166},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26166},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54bcf9002dfd; sha256 77b91e15db20f4964273d13c101d7ad36b40b55eeb1dd02bc3c8e409fc257828},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26166. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Advancing reasoning capabilities allow large language models (LLMs) to tackle increasingly complex problems, while reasoning traces - intermediate steps toward solutions - open up high-stakes applications by enabling human inspection of AI decision-making. However, current approaches prioritize model performance over human interpretability, limiting effective human-AI collaboration. In this study, we design and evaluate a human-centered approach that structures reasoning traces based on self-contained, verifiable steps, enabling users to independently assess and correct AI reasoning. Our approach uses XML-like tags to encode reasoning content and metadata, facilitating targeted feedback. Evaluation on mathematical reasoning tasks shows our approach maintains equivalent performance to standard Chain-of-Thought reasoning while enhancing interpretability. User studies demonstrate significant improvements in perceived usefulness and ease of use. This work advances understanding of how user-centric design of LLM outputs can better serve human collaboration needs in high-stakes AI deployments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26166 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:53.601Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).