A Shaky Voice Is Not Always a Dodge: Benchmarking Textual and Vocal Evasion Detection in Earnings Calls
Year: 2026
Type: conference-paper
Abstract: Existing approaches to evasion detection in earnings calls focus on textual transcripts, treating evasion as a single-dimensional phenomenon.We argue that evasion in spoken communication is inherently multidimensional: beyond what executives say, how they say it carries independent and complementary information.To study these dimensions jointly, we introduce DualEvasion, a benchmark for evasion detection across text and audio in earnings call Q&A.The benchmark contains 505 annotated question-answer pairs from 60 earnings calls, each with two independent labels: textual evasion (direct vs. evasive) and vocal cues operationalized as speaker confidence (confident vs. unconfident).Our experiments show that state-of-the-art multimodal models struggle to detect vocal confidence, particularly on unconfident responses.Our analysis suggests these models interpret acoustic cues in isolation rather than relative to each speaker's baseline.Providing speaker-level references yields modest improvements, but a substantial gap with human performance remains.
Authors: Mirae Kim, Seonghun Jeong, Youngjun Kwak
Institutions: Kakaobank (South Korea), Yonsei University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7204854727