Searcharxiv⌕ Search

arXiv subjects

Eljas Linna

Publications and source records attributed to Eljas Linna.

5 recordsLinked to original sources

RESYNC: Residual Latent-State Synchronization for Deadline-Bound Streaming Inference

Predicting every observation in a high-rate stream requires a model to finish before the next arrival. A large model may offer better predictions but miss that deadline. We propose RESYNC: the large model runs asynchronously, while a fast path updates its latest exact but stale latent state using the observations received since that state was computed and applies its unchanged prediction head. The updater learns from the frozen model's representations without task labels. Across one real and two synthetic streams and five architecture families, RESYNC beats the best compact or distilled alternative with a paired 95% interval above zero in all twelve dataset--architecture pairs with a material teacher advantage at anchor ages of 4--12 observations, and in eleven pairs at older tested ages up to 32. The share of the teacher's gain preserved remains complete on the real stream but is lower and generally declines with anchor age on the synthetic streams. In live replay with 1 ms arrivals, the synchronous large models cannot deliver any predictions on time while RESYNC serves at least 99.4% of arrivals within the interval, with 0.35--0.62 ms median latency on one CPU thread: around the same speed as or faster than the compact model, and 7.9--17.7$\times$ faster than synchronous large-model inference. RESYNC targets settings with background compute available but a strict per-observation response deadline.

cs.LG↗

UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecasting

Forecasting short-horizon mid-price movements from limit order book (LOB) data is central to algorithmic trading, yet most deep LOB forecasters are point predictors: they output a direction or a displacement, but never indicate which of their forecasts can be trusted. We introduce UQ-LOB, a lightweight, encoder-agnostic uncertainty quantification module that attaches to any pretrained LOB encoder and, in the spirit of attentive neural processes, conditions each forecast on a context set of recently completed windows whose outcomes are already realised. The UQ-regression variant outputs a calibrated Gaussian over the future tick displacement, while the UQ-classification variant outputs a categorical distribution over down/up/stationary. Both expose a scalar confidence (predicted signal-to-noise ratio or class probability) that supports selective prediction. On 5.2 billion LOB events across seven cryptocurrency assets and horizons of 5, 10 and 15 seconds, UQ-regression attains near-nominal 68% interval coverage, and restricting to the most confident 10% of predictions raises directional macro F1 by 0.11-0.15 for UQ-regression and 0.05-0.11 for UQ-classification, at every horizon. On large, economically meaningful moves, the tightest confidence tier reaches a directional F1 of 0.88 (down) and 0.83 (up) at the 5-second horizon.

cs.AI↗

Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling

Deep Limit Order Book forecasting models capture nonlinear market dynamics, but their ability to quantify the effects of counterfactual order book messages has not been systematically validated. We introduce a model-agnostic framework that compares a trained forecaster's predictive distributions before and after injecting mechanically valid counterfactual messages, defining short-horizon model-implied market impact. A Transformer-based forecaster recovered scenario rankings with a Spearman correlation of 0.99 and 97.2% directional agreement with realized historical outcomes among non-neutral scenarios. Observation-level analysis further showed that estimated impacts captured incremental sequence-dependent variation beyond scenario identity and the pre-event forecast. These results provide evidence that pretrained Limit Order Book forecasters can be repurposed for scenario-conditioned response modeling without retraining.

cs.LG↗

LOBERT: Generative AI Foundation Model for Limit Order Book Messages

Modeling the dynamics of financial Limit Order Books (LOB) at the message level is challenging due to irregular event timing, rapid regime shifts, and the reactions of high-frequency traders to visible order flow. Previous LOB models require cumbersome data representations and lack adaptability outside their original tasks, leading us to introduce LOBERT, a general-purpose encoder-only foundation model for LOB data suitable for downstream fine-tuning. LOBERT adapts the original BERT architecture for LOB data by using a novel tokenization scheme that treats complete multi-dimensional messages as single tokens while retaining continuous representations of price, volume, and time. With these methods, LOBERT achieves leading performance in tasks such as predicting mid-price movements and next messages, while reducing the required context length compared to previous methods.

cs.AI↗

Challenges for Generative AI in Legal Reasoning

Large Language Models (LLMs) are being integrated into professional domains, yet their limitations in such high-stakes fields as law remain poorly understood. In response, this paper introduces examples of critical challenges to the functioning of generative and other forms of artificial intelligence (AI) as reliable reasoning tools in judicial decision-making. The study deconstructs core requirements and challenges for AI, including the ability to select the correct legal framework across jurisdictions, generate sound arguments based on the doctrine of the sources of law, distinguish ratio decidendi and obiter dicta in case law, resolve ambiguity arising from general clauses like "reasonableness", manage conflicting legal provisions, and apply the burden of proof correctly. The paper maps various AI enhancement mechanisms, such as retrieval-augmented generation (RAG), multi-agent systems and neuro-symbolic AI, to these challenges, assessing their potential to bridge the gap between the probabilistic nature of LLMs and the rigorous, choice-driven demands of legal interpretation. Furthermore, the paper sketches a path towards an evaluation framework, proposing that legal requirements be organized into normative, doctrinal, evidential, and technical categories, and subsequently operationalized into domain-specific, testable design obligations. The findings indicate that these techniques can address specific narrow challenges, but they fail to solve the more significant ones, particularly in tasks requiring discretion and transparent, justifiable reasoning. Therefore, we advocate for a staged adoption, first capturing efficiency in simple cases with technology already available today and sustaining long-term investment in new methods that handle hierarchy, temporality, and other requirements of legally sound reasoning, thus enabling expansion to complex adjudication in the future.

cs.AI↗