发表机构
Beijing Normal-Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出双分支晚期融合框架，结合LLM文本评判与对话音频编码器，检测财报电话会议中的管理层回避，以预测SEC不利事件，AUROC达0.89，优于单一模态。
AI 中文摘要
财报电话会议是管理层在分析师审视下披露信息的主要渠道。先前研究已将声音和词汇线索与未来不利结果联系起来，但通常在整个电话会议中汇总特征，未充分利用问答的互动结构。我们提出一个双分支晚期融合框架，用于检测管理层回避性，作为外部SEC事件（主要是延迟提交）的预测指标：（i）一个LLM作为评判者，通过结构化二元评分标准将问答文本映射为可解释的电话会议级向量X_text；（ii）一个冻结的对话编码器，其时间隐藏状态由DeepVoice风格的顺序读取器读取，以生成音频表示h。对（X_text, h）进行晚期融合，产生电话会议级风险评分p。在n=1,039次电话会议（212次延迟提交）中，采用公司分组5折交叉验证，融合达到AUROC约0.89，而文本评判者为0.55，仅时长特征为0.71。这些结果表明，对话音频动态编码了超越词汇内容和通话时长的管理层回避性，为不利SEC结果提供了更强的早期预警信号。
英文摘要
Earnings conference calls are a primary channel through which managers disclose information under analyst scrutiny. Prior work has linked vocal and lexical cues to future adverse outcomes, but often pools features over an entire call and underuses the interactive structure of Q&A. We propose a two-branch late-fusion framework for detecting managerial evasiveness as a predictor of extrinsic SEC events (primarily late filings): (i) an LLM-as-a-judge that maps Q&A text to an interpretable call-level vector X_text via a structured binary rubric, and (ii) a frozen conversational encoder whose temporal hidden states are read by a DeepVoice-style sequential reader to produce an audio representation h. Late fusion of (X_text, h) yields a call-level risk score p. On n=1,039 calls (212 late filings) with firm-grouped 5-fold CV, fusion reaches AUROC approx. 0.89, versus 0.55 for the text judge and 0.71 for duration alone. These results show that conversational audio dynamics encode managerial evasiveness beyond lexical content and call length, yielding a stronger early-warning signal of adverse SEC outcomes.
