Detecting Corporate AI-Washing via Cross-Modal Semantic Inconsistency Learning
Authors: Zhanjie Wen, Jingqiao Guo
Organizations: School of Economics and Trade, Guangdong University of Finance, Guangzhou 510521, China · Department of Computer Science, Faculty of Science, Hong Kong Baptist University, Hong Kong 999077, China
Corporate AI-washing-the strategic misrepresentation of AI capabilities via exaggerated or fabricated cross-channel disclosures-has emerged as a systemic threat to capital market information integrity with the widespread adoption of generative AI. Existing detection methods rely on single-modal text frequency analysis, suffering from vulnerability to adversarial reformulation and cross-channel obfuscation. This paper presents AWASH, a multimodal framework that redefines AI-washing detection as cross-modal claim-evidence reasoning (instead of surface-level similarity measurement), built on AW-Bench-the first large-scale trimodal benchmark for this task, including 88412 aligned annual report text, disclosure image, and earnings call video triplets from 4892 A-share listed firms during 2019Q1-2025Q2. We propose the Cross-Modal Inconsistency Detection (CMID) network, integrating a tri-modal encoder, a structured natural language inference module for claim-evidence entailment reasoning, and an operational grounding layer that cross-validates AI claims against verifiable physical evidence (patent filing trajectories, AI-specific talent recruitment, compute infrastructure proxies). Evaluated against six competitive baselines, CMID achieves an F1 score of 0.882 and an AUC-ROC of 0.921, outperforming the strongest text-only baseline by 17.4 percentage points and the latest multimodal competitor by 11.3 percentage points. A pre-registered user study with 14 regulatory analysts verifies that CMID-generated evidence reports cut case review time by 43% while increasing true positive detection rates by 28%. These findings confirm the technical superiority and practical applicability of structured multimodal reasoning for large-scale corporate disclosure surveillance.
As artificial intelligence and generative large language models drive industrial upgrading, capital markets increasingly focus on AI-themed listed firms. Information asymmetry and technological opacity lower the cost of exaggerating AI capabilities relative to genuine R&D, spurring widespread AI Washing. Using China's A-share market from 2018Q1 to 2025Q2, we advance literature in measurement and mechanism testing. We construct a multimodal AI Washing Risk Score (AWRS) via Qwen-VL to assess text-image consistency in annual reports and roadshows, and a Material Real-Investment Matching Index (MRMI) from patent quality, AI intangible asset capitalization, and technical personnel compensation using PCA. Four findings emerge: (1) AWRS lacks predictive power for future MRMI, with a wider rhetoric-action gap among financially constrained firms; (2) substantive AI investment boosts high-quality patents, while empty rhetoric crowds out industry innovation; (3) long-horizon institutional investors detect AI Washing through site visits and reduce holdings; (4) such divestment triggers analyst downgrades, retail selling, and sharp valuation corrections within 180 days. Results are robust to IV-2SLS and staggered DID using the ChatGPT shock. This study enhances disclosure and pricing-efficiency research and supports RegTech for curbing thematic speculation.
Wen Zhanjie, Guo Jingqiao
School of Economics and Trade, Guangdong University of Finance, Guangzhou, Guangdong, 510521 · Department of Computer Science, Faculty of Science, Hong Kong Baptist University, Hong Kong, 999077
Word-level detectors identify unedited AI-generated text almost perfectly, but the literature documents their brittleness under rewording, and a word-level score neither characterizes a text nor identifies which AI model wrote it. We ask whether AI-generated text can be identified one level deeper, from structural signatures: how information is presented, in what order, with what evidence, and in what voice. We replicate StoryScope (Russell et al., 2026), which showed such patterns for AI-generated fiction, on commercial content: 2,250 pre-ChatGPT human blog posts from 268 company domains against 11,250 AI mirrors from five frontier models. A 203-feature instrument, applied by an LLM and validated in a human gold-annotation session (human-human kappa 0.939, human-model 0.951), detects AI posts from its 176 structural features alone at 97.0 macro-F1 on held-out companies, nearly unchanged (96.1) when every AI post is reworded by its own model. The signal characterizes and attributes: AI posts share a tidy, self-announcing shape, 68.6% are attributed to the correct source against a 16.7% chance rate, and human posts occupy rare structural configurations. All effects replicate StoryScope's, consistent in direction and at least as large in magnitude. We release pipeline, instrument, prompts, code, and aggregate artifacts.
Claims paired with AI-generated images are a rapidly growing form of misinformation. Existing automated fact-checking (AFC) methods mainly treat this as a provenance problem, detecting low-level synthesis artifacts to decide whether an image is AI-generated. However, such methods do not verify what human fact-checkers often check: whether an image's content is consistent with the context implied by its accompanying claim. To address this gap, we introduce MIC (Multimodal Inconsistency Checking), an AFC framework that assists human fact-checkers by detecting AI-generated multimodal misinformation and explaining inconsistencies using world knowledge. MIC first uses supervised fine-tuning (SFT) for task adaptation and then applies Group Relative Policy Optimization (GRPO) to directly optimize component-level verifiable rewards for verdict prediction, inconsistency type classification, visual evidence description, and world-knowledge explanation. We further introduce MIC-Bench, a benchmark comprising 8,812 image-claim instances derived from 4,406 claims, where each claim is paired with an authentic image and an AI-generated counterpart that introduces a controlled contextual inconsistency. Compared with SFT alone, GRPO further improves Macro-F1 by 4.67 and 4.11 points in the in-distribution and out-of-distribution settings, respectively, while also improving the semantic similarity of visual evidence descriptions and world-knowledge explanations to reference annotations. Our code and data are available at https://github.com/UKPLab/arxiv2026-mic.
Ruihong Zeng, Jonathan Tonglet, Preslav Nakov +1
Mohamed bin Zayed University of Artificial Intelligence, UAE · UKP Lab · Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany +2