arXiv cs.CL· Xiaoyu Ma, Kelvin J. L. Koa, Yuncong Liu, Ke-Wei Huang·· 2 天前AI 评分24
财报电话会 NLP 基准何时算"会后"？论文提出 Availability Contract
When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks
AI 导读
针对财报电话会 NLP 基准中预测目标早于文本或音频输入完成的"事件内时序错配"，论文提出 Availability Contract，要求基准明确输入边界、输入可用性证据、结果起点及所支持结论。
正文 · 原文
Abstract:Corporate financial disclosures often unfold over time, with announcements, prepared remarks, and discussion spanning multiple high-frequency return intervals. Financial NLP benchmarks can therefore suffer from a within-event timing mismatch when the prediction target begins before the textual or audio input used by a model could be complete. Chronological train--test splits do not prevent this mismatch, because it occurs inside individual events rather than across samples. We introduce an Availability Contract, which requires a benchmark to state the input boundary, evidence for input availability, the outcome start, and the claims supported by that evidence. We apply this framework to 552 earnings calls from 24 firms. For each call, we hold the return endpoint fixed and compare the previous close, a documentary call-start proxy, and a completion proxy based on reconstructed audio end plus a stipulated processing allowance. At this baseline, moving from the call-start proxy to the completion proxy flips return signs for 9.4% of calls. Holding completion-clock cutpoints fixed, 28.3% change quintile. In an independent release-session analysis of a public earnings-call volatility benchmark, shifting before-market target windows forward by one trading session raises three-day mean squared error by 18.1-21.4% across four frozen prediction streams, while their point rankings remain unchanged. Together, the results show that labels and losses can depend materially on the declared outcome clock even when model rankings appear stable. The Availability Contract makes this assumption explicit and ties post-input claims to the available timing evidence.
| Comments: | ICAIF 2026 |
| Subjects: | Computational Finance (q-fin.CP); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.21659 [q-fin.CP] |
| (or arXiv:2610.21659v1 [q-fin.CP] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21659 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1145/3858063.3858902
DOI(s) linking to related resources |
Submission history
From: Kelvin Koa [view email]
[v1]
Thu, 15 Oct 2026 10:40:06 UTC (6,034 KB)
来源：arXiv cs.CL · arxiv.org