As post-training techniques evolve, large language models (LLMs) are increasingly augmented with structured multi-step reasoning abilities, often optimized through reinforcement learning. These reasoning-enhanced models outperform standard LLMs on complex tasks and now underpin many commercial LLM APIs. However, to protect proprietary behavior and reduce verbosity, providers typically conceal the reasoning traces while returning only the final answer. This opacity introduces a critical transparency gap: users are billed for invisible reasoning tokens, which often account for the majority of the cost, yet have no means to verify their authenticity. This opens the door to token count manipulation, where providers may overreport token usage or inject synthetic, low-effort tokens to inflate charges, a threat that can be carried out at near-zero cost. To address this issue, we propose CoIn, a verification framework that audits both the quantity and semantic validity of hidden tokens. CoIn constructs a verifiable hash tree from token embedding fingerprints to check token counts, and uses embedding-based relevance matching to detect fabricated reasoning content. Experiments demonstrate that CoIn, when deployed as a trusted third-party auditor, can effectively detect token count manipulation with a success rate reaching up to 94.7%, demonstrating a strong ability to restore billing transparency in opaque LLM services. The dataset and code are available at https://github.com/CASE-Lab-UMD/LLM-Auditing-CoIn .

Large language models (LLMs) are increasingly applied to finance, yet challenges remain in aligning their capabilities with real-world institutional demands. In this survey, we provide a systematic, dual-perspective review bridging financial practice and LLM research. From a practitioner-centric standpoint, we introduce a functional taxonomy covering five core financial domains—Data Analysis, Investment Research, Trading, Investment Management, and Risk Management—mapping each to representative tasks, datasets, and institutional constraints. From a research-focused perspective, we analyze key modeling challenges, including numerical reasoning limitations, prompt sensitivity, and lack of real-time adaptability. We comprehensively catalog over 30 financial benchmarks and 20 representative models, and compare them across modalities, tasks, and deployment limitations. Finally, we identify open challenges and outline emerging directions such as continual adaptation, coordination-aware multi-agent systems, and privacy-compliant deployment. We emphasize deeper researcher–practitioner collaboration and transparent model architectures as critical pathways to safer and more scalable AI adoption in finance.