LLM压缩财报会扭曲投资决策，需评估其对关键信息的保留程度。
When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis
- 提出多候选压缩+差异审计机制，提升压缩内容的决策保真度。
- 实验证明：压缩后内容虽流畅且看似合理，却常改变原始判断结果。
- 适合金融智能系统设计者与合规审查人员参考。
金融决策者面临的信息量超过可直接分析的范围，因此需要上下文压缩。然而，当大语言模型（LLMs）压缩财务资料时，可能改变原始资料支持的投资判断。我们将其问题定义为信息保真度：压缩若改变了源材料引发的决策，则保真度下降。在代理系统中，此类损失可能在中间步骤反复出现并累积放大。在财务报告和业绩说明会记录中，我们发现基于LLM的压缩能生成流畅且事实合理的摘要，但依然会改变下游决策。我们分析了两种与保真度损失相关的诊断模式：去背景化（关键证据被保留但脱离必要警告和语境限定），以及模型依赖性（不同压缩器对同一源呈现不同视角）。随后提出代理式上下文压缩方法，通过生成多个候选压缩版本，并审计其与原始来源的不一致之处。结果表明，金融压缩不仅需评估效率或事实性，更应关注其对决策相关语境的保留能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。