Metraipolis › archive › dc_55f79f574277

Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions — arXiv:2609.38869

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38869
License (as archived)
CC0-1.0
Archived
2026-10-07T12:42:17.149Z
SHA-256 of the archived text
aa72c67783c027609bb59bd90e90cbfa4fa24cd378461023246904c4ea69f893
Stable URL of this page
https://metraipolis.com/documento/dc_55f79f574277

How to cite

Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions — arXiv:2609.38869 — arXiv (en), https://arxiv.org/abs/2609.38869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55f79f574277 (Metraipolis archive dc_55f79f574277, sha256 aa72c67783c027609bb59bd90e90cbfa4fa24cd378461023246904c4ea69f893)
BibTeX
@misc{dc55f79f574277,
  title = {Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions — arXiv:2609.38869},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38869},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55f79f574277; sha256 aa72c67783c027609bb59bd90e90cbfa4fa24cd378461023246904c4ea69f893},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to understand. While large language models (LLMs) can translate these outputs into natural language, they may produce errors when inferring numerical changes and feature relations. We propose an LLM narrative framework for cross-sectional stock return prediction that combines temporal Shapley additive explanations (SHAP) evidence with historical regime analogs. Temporal evidence tracks changes in the normalized global SHAP importance of an XGBoost model over six months. Historical analogs are past periods with similar changes in SHAP importance, their model performance and subsequent market returns are provided as comparative context. Using this framework, we conduct a controlled study of progressive reasoning externalization, sequentially providing raw SHAP sequences, deterministic temporal descriptors, and feature relations. Each generated claim is verified against provenance-linked evidence. Across Qwen3, externalizing numerical and relational reasoning improved evidence faithfulness as well as temporal and relational accuracy. Evidence faithfulness increased from 0.696 to 0.996 for Qwen3-32B-Instruct. While historical analogs did not improve structured automatic faithfulness, they received higher human-rated usefulness scores. These results suggest that externalizing verifiable reasoning enhances narrative faithfulness and that historical context adds interpretive value.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE).
Pagina del lavoro: https://arxiv.org/abs/2609.38869 — 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 2026-10-07T12:14:13.702Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).