Detecting whether corporate sustainability disclosures truly satisfy reporting standards is essential for greenwashing-aware ESG auditing, yet existing resources rarely evaluate whether disclosures sufficiently satisfy framework metrics. We introduce MM-COMPLIANCE, a multilingual multimodal dataset aligned with SASB metrics across six languages (English, French, Japanese, Chinese, Thai, and Korean), with page-level evidence and a key completeness annotation that separates fully compliant disclosures from partial mentions. We define two tasks reflecting practical auditing workflows: Page-level Compliance Judgment and Metric-to-Page Evidence Retrieval. Our evaluated baselines primarily comprising open-source architectures, supplemented by a commercial VLM as an upper-bound reference, show moderate performance for page understanding and evidence localization, but consistently low performance on partial compliance verification and large variation across languages and industries. MM-COMPLIANCE provides a benchmark for developing framework-aware models to support rigorous ESG compliance auditing and long-term commitment tracing.

Demand for personalized financial advice is growing, yet current LLM-based advisors often fail to provide consistent and specialized guidance. Simple persona prompts rarely specify how a financial advisor should reason and often drift toward generic recommendations. We propose Fund2Persona, a framework that builds financial-advisor personas from real-world fund disclosures and refines them through an actor–scorer–patcher loop. We test whether the resulting personas can predict held-out portfolio changes and produce commentary consistent with fund managers’ own explanations. They outperform generic baselines on both tasks. We further study two downstream diagnostics: market-scenario generation, where persona retrieval broadens plausible investment views, and multi-turn investor–advisor conversations, where matched personas give more specific and useful advice than a generic advisor. These results suggest that real fund data can bring manager-specific investment expertise to LLM advisors rather than merely changing an LLM’s surface style.

Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they can alter the investment judgment supported by the original source. We frame this problem as information fidelity: compression loses fidelity when it changes the decision induced by the source. In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process. Across financial filings and earnings-call transcripts, we find that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions. We analyze two diagnostic patterns associated with fidelity loss: decontextualization, where salient evidence is retained but separated from the caveats and contextual qualifiers needed for correct interpretation, and model dependency, where different compressors expose different views of the same source. We then propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source. Our results suggest that financial compression should be evaluated not only by efficiency or factuality, but also by its ability to preserve decision-relevant context.

Natural language processing (NLP) has been widely used in quantitative finance, but traditional methods often struggle to capture rich narratives in textual data, leaving potentially informative signals under-explored. Large language models (LLMs) offer a promising alternative as they are able to extract nuanced semantics. In this paper, we ask whether semantic signals extracted by LLMs from corporate disclosures predict abnormal returns (alpha) beyond broad market movements and common risk factors. We introduce a simple framework, *LLM as extractor, embedding as ruler*, which extracts context-aware, metric-focused textual spans and quantifies semantic changes across consecutive disclosure periods using embedding similarity. This allows us to measure the degree of metric shifting - how much firms move away from previously emphasized metrics, referred to as moving targets. In portfolio and cross-sectional regression tests against a recent traditional baseline, our method yields a moving-targets signal that delivers significant risk-adjusted alpha. Qualitative analysis suggests that these gains stem from preserving contextual qualifiers and filtering out non-metric terms that traditional approaches often miss.

Prediction markets provide a unique setting where event-level time series are directly tied to natural-language descriptions, yet discovering robust lead–lag relationships remains challenging due to spurious statistical correlations. We propose a hybrid two-stage causal screener to address this challenge: (i) a statistical stage that uses Granger causality to identify candidate leader–follower pairs from market-implied probability time series, and (ii) an LLM-based semantic stage that re-ranks these candidates by assessing whether the proposed direction admits a plausible economic transmission mechanism based on event descriptions. Because causal ground truth is unobserved, we evaluate the ranked pairs using a fixed, signal-triggered trading protocol that maps relationship quality into realized profit and loss (PnL).On Kalshi Economics markets, our hybrid approach consistently outperforms the statistical baseline. Across rolling evaluations, the win rate increases from 51.4% to 54.5%. Crucially, the average magnitude of losing trades decreases substantially from 649 USD to 347 USD. This reduction is driven by the LLM’s ability to filter out statistically fragile links that are prone to large losses, rather than relying on rare gains. These improvements remain stable across different trading configurations, indicating that the gains are not driven by specific parameter choices. Overall, the results suggest that LLMs function as semantic risk managers on top of statistical discovery, prioritizing lead–lag relationships that generalize under changing market conditions.