当摘要扭曲决策：LLM 压缩金融分析中的信息保真度

Computer Science > Artificial Intelligence arXiv:2606.29251 (cs) [Submitted on 28 Jun 2026 (v1), last revised 17 Sep 2026 (this version, v3)] Title:When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis Authors:Hoyoung Lee, Suhwan Park, Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, CheolWon Na, Zhangyang Wang, Zach Golkhou, Minkyu Kim, Sotirios Sabanis, Alejandro Lopez-Lira, Dhagash Mehta, Soonyoung Lee, Chanyeol Choi, Wonbin Ahn, Yongjae Lee View a PDF of the paper titled When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis, by Hoyoung Lee and 17 other authors View PDF HTML (experimental) Abstract:Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they can alter the investment judgment supported by the original source. We frame this problem as information fidelity: compression loses fidelity when it changes the decision induced by the source. In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process. Across financial filings and earnings-call transcripts, we find that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions. We analyze two diagnostic patterns associated with fidelity loss: decontextualization, where salient evidence is retained but separated from the caveats and contextual qualifiers needed for correct interpretation, and model dependency, where different compressors expose different views of the same source. We then propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source. Our results suggest that financial compression should be evaluated not only by efficiency or factuality, but also by its ability to preserve decision-relevant context. Comments: Subjects: Artificial Intelligence (cs.AI); Computational Finance (q-fin.CP) Cite as: arXiv:2606.29251 [cs.AI] (or arXiv:2606.29251v3 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2606.29251 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hoyoung Lee [view email] [v1] Sun, 28 Jun 2026 07:44:54 UTC (341 KB) [v2] Wed, 8 Jul 2026 11:36:35 UTC (336 KB) [v3] Thu, 17 Sep 2026 15:02:17 UTC (349 KB) Full-text links: Access Paper: View a PDF of the paper titled When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis, by Hoyoung Lee and 17 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI new | recent | 2026-06 Change to browse by: cs q-fin q-fin.CP References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)