arXiv subjects

Kemal Kirtac

Publications and source records attributed to Kemal Kirtac.

5 recordsLinked to original sources

arXiv2026

ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift

Ethereum decentralized finance (DeFi) provides a public, time-stamped record of transaction-level event streams, but the same public symbols can create strong machine-learning shortcuts. We introduce ETH-TraceBench, a benchmark for evaluating Ethereum DeFi representations under temporal, protocol, pool/infrastructure, and symbolic shift. The raw event universe covers January 2021-December 2025 and contains 1.35 billion transactions with logs and 5.01 billion raw log rows. Model evaluation uses a fixed 911,267-instance supervised sample, training on 2021-2024, selecting models on 2025H1, and testing on 2025H2. Simple models perform strongly on the aggregate temporal test: TraceStats-GB reaches 0.953 macro-F1 and TopicEmitterHashMLP 0.959 on the canonical DEX test set. Performance drops sharply under protocol novelty, with macro-F1 of 0.794, 0.743, and 0.766 for TraceStats-GB, TopicEmitterTrace-SGD, and TopicEmitterHashMLP, while strict unseen-pool scores remain 0.927, 0.897, and 0.935. Uniswap v4 and Ekubo v1, both absent from supervised training, are materially harder than the full test. Jointly masking emitter and topic identity reduces DEX macro-F1 to 0.916 and liquidation macro-F1 to 0.774 for TopicEmitterTrace-SGD. A standard Transformer over log-index-ordered events provides no consistent advantage over a deterministic shuffle of the same events, indicating that high aggregate scores can arise without sophisticated chronological modeling. A natural-prevalence audit estimates 2025H2 DEX prevalence among logged Ethereum transactions at about 22.5%, and a deterministic 400-transaction audit finds complete agreement with task label sources and independently re-queried raw-log counts. ETH-TraceBench therefore treats difficult transfer and controlled-input conditions, rather than a single aggregate score, as the main evaluation target.

cs.LG↗

arXiv2026

Financial Language Models as Applied Artificial Intelligence Systems for News-Based Trading under Market Frictions

Financial language models can transform unstructured firm-specific news into structured decision signals, but financial AI research lacks an integrated deployment framework for evaluating whether those signals remain useful in financial decision systems. Computer science research has developed strong methods for time-series forecasting, text classification, multimodal stock prediction, graph-based market modeling, and machine-learning operations, yet these streams do not provide a domain-specific protocol that jointly tests financial language-model outputs under event-time observability, probability calibration, execution timing, transaction costs, liquidity constraints, capacity limits, operational diagnostics, and statistical inference. We introduce MFAST, a Market-Friction-Aware Sentiment-to-Trading framework that converts timestamped financial text into auditable, reproducible, and market-feasible trading decisions. The application is news-based trading, where firm-specific text must be linked to securities before portfolio decisions can be evaluated. The framework links Refinitiv News Analytics to Center for Research in Security Prices (CRSP) equity data, restricts the primary out-of-sample evaluation to post-release news outside disclosed foundation-model data-freshness periods, and adds a public replication arm using open financial text and public price data. Results show that decoder-only language models outperform encoder baselines and dictionary sentiment in classification, calibration, return prediction, and net portfolio performance, while operational diagnostics reveal trade-offs among accuracy, latency, memory, throughput, and inference cost. The paper shows that credible evaluation of financial language models requires an end-to-end engineering approach combining language understanding, temporal discipline, market-friction-aware deployment, and reproducible validation.

cs.CL↗

arXiv2026

Learning to Aggregate Zero-Shot LLM Agents for Corporate Disclosure Classification

This paper studies whether a lightweight supervised aggregator can combine diverse zero-shot large language model outputs into a stronger downstream signal for corporate disclosure classification. Zero-shot LLMs can read disclosures without task-specific fine-tuning, but their predictions often vary across prompt perspectives, model families, and confidence levels. I examine this problem with a multi-prompt framework in which three fixed zero-shot LLM classifiers read each disclosure from different financial perspectives and output a sentiment label, a confidence score, and a short rationale. A logistic meta-classifier then aggregates these outputs to predict next-day stock return direction. To reduce pretrained-model contamination, I restrict evaluation to a post-release sample of 9{,}860 U.S.\ corporate disclosures issued by large publicly traded firms between January 2025 and March 2026, after the release of the frozen base LLMs used in the experiment. Results show that the trained aggregator outperforms single classifiers, majority vote, confidence-weighted voting, a zero-shot LLM judge, and a FinBERT baseline. Balanced accuracy rises from 0.566 for the best single classifier to 0.606 for the trained aggregator. The gain is largest in mixed-signal disclosures where classifiers disagree. The results suggest that zero-shot LLM outputs contain complementary financial signals, while also showing that the strongest gains come from supervised aggregation rather than from zero-shot voting alone.

q-fin.TR↗

arXiv2025

Large language models in finance : what is financial sentiment?

Financial sentiment has become a crucial yet complex concept in finance, increasingly used in market forecasting and investment strategies. Despite its growing importance, there remains a need to define and understand what financial sentiment truly represents and how it can be effectively measured. We explore the nature of financial sentiment and investigate how large language models (LLMs) contribute to its estimation. We trace the evolution of sentiment measurement in finance, from market-based and lexicon-based methods to advanced natural language processing techniques. The emergence of LLMs has significantly enhanced sentiment analysis, providing deeper contextual understanding and greater accuracy in extracting sentiment from financial text. We examine how BERT-based models, such as RoBERTa and FinBERT, are optimized for structured sentiment classification, while GPT-based models, including GPT-4, OPT, and LLaMA, excel in financial text generation and real-time sentiment interpretation. A comparative analysis of bidirectional and autoregressive transformer architectures highlights their respective roles in investor sentiment analysis, algorithmic trading, and financial decision-making. By exploring what financial sentiment is and how it is estimated within LLMs, we provide insights into the growing role of AI-driven sentiment analysis in finance.

q-fin.ST↗

arXiv2024

Sentiment trading with large language models

We investigate the efficacy of large language models (LLMs) in sentiment analysis of U.S. financial news and their potential in predicting stock market returns. We analyze a dataset comprising 965,375 news articles that span from January 1, 2010, to June 30, 2023; we focus on the performance of various LLMs, including BERT, OPT, FINBERT, and the traditional Loughran-McDonald dictionary model, which has been a dominant methodology in the finance literature. The study documents a significant association between LLM scores and subsequent daily stock returns. Specifically, OPT, which is a GPT-3 based LLM, shows the highest accuracy in sentiment prediction with an accuracy of 74.4%, slightly ahead of BERT (72.5%) and FINBERT (72.2%). In contrast, the Loughran-McDonald dictionary model demonstrates considerably lower effectiveness with only 50.1% accuracy. Regression analyses highlight a robust positive impact of OPT model scores on next-day stock returns, with coefficients of 0.274 and 0.254 in different model specifications. BERT and FINBERT also exhibit predictive relevance, though to a lesser extent. Notably, we do not observe a significant relationship between the Loughran-McDonald dictionary model scores and stock returns, challenging the efficacy of this traditional method in the current financial context. In portfolio performance, the long-short OPT strategy excels with a Sharpe ratio of 3.05, compared to 2.11 for BERT and 2.07 for FINBERT long-short strategies. Strategies based on the Loughran-McDonald dictionary yield the lowest Sharpe ratio of 1.23. Our findings emphasize the superior performance of advanced LLMs, especially OPT, in financial market prediction and portfolio management, marking a significant shift in the landscape of financial analysis tools with implications to financial regulation and policy analysis.

q-fin.CP↗