Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information

Ahmet Efe; Shivank Sapra; Bilal Ahmed

cs.CLOct 31, 2026

Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information

Authors: Ahmet Efe, Shivank Sapra, Bilal Ahmed

Organizations: University of Minnesota, Minneapolis, MN, USA

Abstract

Financial restatements correct errors in previously published financial reports. Could managers' language in earnings calls warn of them in advance? Comparing 109 calls that precede restatements with 218 matched control calls, we find that the text predicts restatements but adds no detectable ranking gain beyond public firm information. A text classifier beats chance, largely because of restatements tied to special-purpose acquisition companies, but a model using only public information scores slightly higher. With refitting, the 95% interval for the gain from adding text (-0.05 to 0.11 AUROC) still leaves room for a meaningful benefit. A large language model scores higher, but we show that it names the exact ticker in 66% of masked transcripts, and it was released after the restatements occurred. Our results suggest that finding new warning signs in call text requires a public-information baseline and a check of what a language model already knows.

Figures & tables

Figure 1: Within-set AUROC on 109 matched sets with 95% confidence intervals. The dashed line marks chance, and the dotted line marks the 0.60 threshold. The name-only bar gives the 27B model only the firm’s name and the call date. † The 27B model names the exact ticker in most masked transcripts (see the language-model results).

Setting (sets)	Baseline	Text	$\Delta$ [95% CI]
Main (109)	0.651	0.628	$0.000$ [ $-$ .06, .06]
$\pm$ 3-yr controls (109)	0.683	0.665	$+0.005$ [ $-$ .05, .06]
No SPAC-related (80)	0.625	0.562	$-0.025$ [ $-$ .08, .03]
Out-of-time (69)	0.594	0.572	$+0.014$ [ $-$ .03, .06]

Table 1: Within-set AUROC of the baseline and the text model, and the change

\Delta

when text is added to the baseline. Intervals hold the models fixed.

\pm

3-yr: controls with no Item 4.02 observed within three years of the call. No SPAC-related: models retrained without SPAC-related cases. Out-of-time: trained on the 40 sets filed by 2019 and tested on the later sets. Definitions are in Appendix A .

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

	Cases	Controls
Calls	109	218
Distinct firms	106	218
Motley Fool corpus	61	122
S&P 500 corpus	48	96
Calls in 2005–2014	28	56
Median words	8,308	8,682

Appendix

Table 2: Dataset summary. Each control matches its case’s corpus and quarter.

Figure 2: Text-model performance by time between the call and the restatement filing. Within each window, scores are averaged over each firm’s calls. A matched set is included when the case and at least one control have a call in that window (77, 93, 66, and 36 sets). Calls are scored by models that did not train on the firm.

Financial Forecasting

Financial forecasting uses market, company, and economic data to predict prices, returns, volatility, and business outcomes for decisions and risk management.

See all 95 papers

When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks
Oct 15, 2026Xiaoyu Ma, Kelvin J. L. Koa, Yuncong Liu +1Look-Ahead Bias in Language Models Forecasting Benchmarks
National University of Singapore Asian Institute of Digital Finance Singapore
Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls
May 4, 2026Rasmus T. Aavang, Rasmus Tjalk-Bøggild, Alexandre Iolov +3Document Information Extraction LLM Information Extraction
Department of Computer Science, Aalborg University, Denmark · ALIPES ApS, Denmark · University of Copenhagen
Lie to me: Detecting Managerial Evasiveness in Earnings Calls via Conversational Audio Encoders
Sep 12, 2026Huizhong Chen, Huan Zhang
Beijing Normal-Hong Kong Baptist University · Individual researcher

Oct 15, 2026J/K move · Enter open · S save

When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks

Xiaoyu Ma, Kelvin J. L. Koa, Yuncong Liu, Ke-Wei Huang

National University of Singapore Asian Institute of Digital Finance Singapore

Look-Ahead Bias in Language Models Forecasting Benchmarks Financial Forecasting Financial Time Series

Open paper AskPDF arXiv

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.

Abstract

Financial Forecasting

Explore similar work

When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks

Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls

Lie to me: Detecting Managerial Evasiveness in Earnings Calls via Conversational Audio Encoders