Study constructs a Japanese financial LLM benchmark.
problem Need for domain-specific benchmarks for LLMs.
method Constructed a benchmark with multiple Japanese and financial domain tasks.
result GPT-4 outperforms other models in the benchmark.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Benchmark Construction”
The paper clarifies conditions for using benchmark scores in machine learning.
problem Using benchmark scores to draw scientific inferences about learning problems.
method Developing conditions of construct validity inspired by psychological measurement theory.
result Clarifies conditions under which benchmark scores support diverse scientific claims.
We give an explicit formulaic algorithm and source code for building long-only benchmark portfolios and then using these benchmarks in long-only market outperformance strategies. The benchmarks (or the corresponding betas) do not involve any principal components, nor do they require iterations. Instead, we use a multif…
Paper examines LLM capability benchmarks through construct validity, favoring nomological account.
problem Linking theoretical capabilities to empirical measurements in LLMs.
method Contrasts three frameworks: nomological, inferential, and causal.
result Nomological account provides best foundation for LLM research.
CleverHans is a software library that provides standardized reference implementations of adversarial example construction techniques and adversarial training. The library may be used to develop more robust machine learning models and to provide standardized benchmarks of models' performance in the adversarial setting. …
The optimization of algorithm (hyper-)parameters is crucial for achieving peak performance across a wide range of domains, ranging from deep neural networks to solvers for hard combinatorial problems. The resulting algorithm configuration (AC) problem has attracted much attention from the machine learning community. Ho…
Framework generates multimodal datasets with known MI for benchmarking.
problem Benchmarking mutual information estimators and SSL techniques.
method Flow-based generative model and structured causal framework.
result Regression performance improves with increasing MI between modalities.
Survey on automating geometry problem solving with large models.
problem Automating geometric problem solving with spatial understanding and logical reasoning.
method Synthesizes GPS advancements through benchmark construction, parsing, and reasoning paradigms.
result Unified analytical paradigm and emerging opportunities identified.
Constructing a Portfolio Optimization Benchmark Framework for Evaluating Large Language Modelsq-fin.PM
Study benchmarks LLMs in portfolio optimization tasks.
problem Evaluate financial decision-making of LLMs.
method Mathematically explicit portfolio optimization problems with multiple-choice questions.
result Distinct performance patterns among LLMs in different financial tasks.
State-of-the-art machine learning methods exhibit limited compositional generalization. At the same time, there is a lack of realistic benchmarks that comprehensively measure this ability, which makes it challenging to find and evaluate improvements. We introduce a novel method to systematically construct such benchmar…
Study characterizes harmful low-fidelity data sources for surrogate models.
problem Identifying which low-fidelity data sources to use in constructing surrogate models.
method Employed benchmark filtering techniques to assess harmful sources using limited data.
result Provided guidelines for using low-fidelity sources in an industrial setting.
We solve the multi-criteria benchmarking problem by formalizing it as a social choice problem and identifying conditions for meaningful rankings.
problem Aggregating multiple metrics into a single ranking for models in benchmarking problems.
method Formalizing multi-criteria benchmarking as a social choice problem and identifying sufficient conditions for meaningful rankings.
result We prove that meaningful multi-criteria benchmarking becomes possible under certain preference conditions (single-peaked, group-separable, distance-restricted).
The past few years have seen a surge of applying Deep Learning (DL) models for a wide array of tasks such as image classification, object detection, machine translation, etc. While DL models provide an opportunity to solve otherwise intractable tasks, their adoption relies on them being optimized to meet latency and re…
In stochastic portfolio theory, a relative arbitrage is an equity portfolio which is guaranteed to outperform a benchmark portfolio over a finite horizon. When the market is diverse and sufficiently volatile, and the benchmark is the market or a buy-and-hold portfolio, functionally generated portfolios introduced by Fe…
Paper introduces TAP-Vid, a benchmark for tracking any point in videos.
problem Tackles the problem of tracking arbitrary physical points on surfaces over longer video clips.
method Formalizes the problem as TAP, introduces TAP-Vid benchmark, uses crowdsourced pipeline with optical flow estimates, proposes TAP-Net model.
result TAP-Net outperforms all prior methods on TAP-Vid benchmark when trained on synthetic data.
Auto-PyTorch automates deep learning by optimizing neural architectures and hyperparameters.
problem Automated deep learning for tabular data with robust and efficient optimization.
method Combines multi-fidelity optimization, portfolio construction, and warmstarting with ensembling.
result Achieves state-of-the-art performance on tabular benchmarks.
Benchmark data sets are an indispensable ingredient of the evaluation of graph-based machine learning methods. We release a new data set, compiled from International Planning Competitions (IPC), for benchmarking graph classification, regression, and related tasks. Apart from the graph construction (based on AI planning…
This work introduces a new benchmark to compare neural network training algorithms.
problem Lack of reliable benchmarks to compare training algorithms effectively.
method Developed a new benchmark called AlgoPerf: Training Algorithms benchmark.
result Demonstrated the feasibility of the benchmark and set a provisional state-of-the-art.
We introduce a principled approach for unsupervised structure learning of deep neural networks. We propose a new interpretation for depth and inter-layer connectivity where conditional independencies in the input distribution are encoded hierarchically in the network structure. Thus, the depth of the network is determi…
Confidence Interval Construction for Multivariate time series using Long Short Term Memory Networkstat.ME
Paper proposes new method for time series confidence intervals using LSTM.
problem Constructing accurate confidence intervals for multivariate time series.
method Uses Long Short Term Memory Network (LSTM) and novel block bootstrap techniques.
result Demonstrates improved accuracy in constructing confidence intervals.
This study benchmarks anomaly detection methods in a functional setup.
problem Efficient anomaly detection in high-frequency sensor data.
method Functional analysis approach for multivariate data.
result Comparison of anomaly detection methods on real datasets.
We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each compound separately. These fingerprints are further transformed non-linearly, their inner-product …
We consider the problem of portfolio selection within the classical Markowitz mean-variance framework, reformulated as a constrained least-squares regression problem. We propose to add to the objective function a penalty proportional to the sum of the absolute values of the portfolio weights. This penalty regularizes (…
A framework and benchmark for deep batch active learning in neural networks.
problem Efficiently acquiring labels for neural network regression.
method Framework of base kernels, transformations, and selection methods; use of sketched finite-width neural tangent kernels and clustering.
result Proposed method outperforms state-of-the-art on benchmark, scales to large data sets.
DOFEN improves DNN performance on tabular data benchmarks.
problem DOFEN tackles the performance gap between DNNs and tree-based models on tabular data.
method DOFEN uses a two-level rODT forest ensembling process inspired by oblivious decision trees.
result DOFEN achieves state-of-the-art results on the Tabular Benchmark.
The paper presents a framework for optimizing crypto-currency portfolios using generative models.
problem Optimizing crypto-currency portfolios using generative models.
method The approach involves evaluating diverse pairings of generative model forecasts and objective functions, using simulations and blending strategies.
result Eclectic blended portfolios outperform individual generative model-based portfolios.
Study builds a Japanese financial-specific LLM through continual pre-training.
problem Lack of domain-specific Japanese financial LLMs.
method Continual pre-training on Japanese financial-focused datasets using a base Japanese LLM.
result Tuned model outperforms original model on Japanese financial benchmarks.
Method for creating synthetic multi-fidelity data sets.
problem Lack of representative synthetic datasets for multifidelity optimisation benchmarks.
method Systematic generation of synthetic fidelities from preexisting datasets.
result Allows systematic investigation of lower fidelity proxies' influence.
Simple model uses time series momentum to outperform benchmarks in equity and bond markets.
problem Finding systematic excess returns in various markets.
method Time series momentum applied to multiple investable indices without complex parameter estimation.
result Significant outperformance in equity and bond markets, nearly doubling returns.
Evaluating Structured Strategy Backtests: Peer Benchmarks, Regime Timing, and Live Performanceq-fin.PM
Backtests of structured strategies lose much of their predictive power in live trading.
problem Uncertainty in how marketed backtests predict live performance of structured strategies.
method Analysis of 1,726 structured strategies from ten global institutions.
result Raw backtests have limited portability into live trading and deteriorate sharply.
There are more than eight hundred interest rates published in China bond market every day. Which are the benchmark interest rates that have broad influences on most interest rates is a major concern for economists. In this paper, multi-variable Granger causality test is developed and applied to construct a directed net…
UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videosq-fin.GN
UniFinEval benchmarks financial models across text, images, and videos.
problem Challenges in evaluating financial multimodal models across text, images, and videos.
method Proposes UniFinEval, a unified multimodal benchmark for financial scenarios.
result Gemini-3-pro-preview achieves best performance but still lags behind experts.
EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statementsq-fin.ST
EDINET-Bench evaluates LLMs on complex financial tasks using Japanese financial statements.
problem Challenges in evaluating LLMs on financial tasks due to specialized expertise and scarce benchmarks.
method Developed EDINET-Bench, an open-source Japanese financial benchmark for LLMs on tasks like fraud detection and earnings forecasting.
result State-of-the-art LLMs perform only marginally better than logistic regression in financial tasks, highlighting the need for more realistic benchmarks.
FinSurvival provides a large-scale financial survival modeling benchmark.
problem Lack of large-scale, realistic, and freely available datasets for benchmarking AI survival models.
method Derived 16 survival modeling tasks from cryptocurrency lending data using an automated pipeline.
result Demonstrated that existing AI survival models are not well-suited for these challenging tasks.
New method compares classifiers using GSD-front, addressing statistical uncertainty and robustness.
problem Comparing classifiers with multiple quality metrics and statistical uncertainty.
method Proposes GSD-front and statistical tests for robust comparisons.
result Reliable method for comparing classifiers with statistical uncertainty and robustness.
Paper benchmarks mutual info estimators on diverse distributions.
problem Evaluating mutual information estimators on complex, real-world distributions.
method Constructs a diverse family of known-ground truth distributions, proposes a benchmark platform.
result Highlights differences in classical and neural estimators' performance across various conditions.
The paper generalizes the construction by stochastic flows of consistent utility processes introduced by M. Mrad and N. El Karoui in (2010). The utilities random fields are defined from a general class of processes denoted by $\GX$. Making minimal assumptions and convex constraints on test-processes, we construct by co…
ECSEL learns signomial equations for explainable classification.
problem Creating interpretable models for classification.
method ECSEL constructs signomial equations directly for classification and explanation.
result ECSEL outperforms state-of-the-art methods in interpretability and efficiency.
Auditing fairness of decision-makers is now in high demand. To respond to this social demand, several fairness auditing tools have been developed. The focus of this study is to raise an awareness of the risk of malicious decision-makers who fake fairness by abusing the auditing tools and thereby deceiving the social co…
In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by usin…
Framework uses LLMs to automate strategy finding in quantitative finance.
problem Brittleness of traditional deep learning models in financial applications.
method Three-stage framework with prompt-engineered LLMs, multimodal agent-based evaluation, and dynamic weight optimization.
result Robust performance in Chinese & US markets, superior risk-adjusted performance.
Quantum codes on hyperbolic lattices outperform Euclidean ones with higher rates and lower overhead.
problem Improving quantum error correction performance with hyperbolic lattices.
method Unified framework using Hyperbolic Cycle Basis algorithm for CSS codes construction and benchmarking.
result Achieved higher encoding rates and lower qubit overhead in hyperbolic quantum error correction codes.
New statistical model improves protein alignment accuracy.
problem Improving accuracy in protein sequence alignment.
method Inferred a time-dependent Markov process from protein sequences.
result Developed a new optimal matrix (MMLSUM) for protein alignment.
BloombergGPT is a large language model trained on financial data, outperforming existing models on financial tasks.
problem Lack of specialized large language models for finance.
method Trained on a 363 billion token dataset augmented with 345 billion tokens from general datasets, using a 50 billion parameter model.
result BloombergGPT outperforms existing models on financial tasks without sacrificing performance on general LLM benchmarks.
We introduce a new general framework for constructing the best trading strategy for a given historical indicator. We construct the unique trading strategy with the highest expected return. This optimal strategy may be implemented directly, or its expected return may be used as a benchmark to evaluate how far away from …
PredictionMarketBench benchmarks trading agents on prediction markets.
problem Evaluating trading agents on prediction markets with realistic conditions.
method Deterministic replay of historical data, execution-realistic simulator, agent interface.
result Fee-aware algorithmic strategies outperform naive agents in volatile episodes.
Considering the classification problem, we summarize the nonparallel support vector machines with the nonparallel hyperplanes to two types of frameworks. The first type constructs the hyperplanes separately. It solves a series of small optimization problems to obtain a series of hyperplanes, but is hard to measure the …
FinReflectKG - EvalBench benchmarks financial KG extraction from SEC 10-K filings.
problem Lack of universal benchmark and evaluation framework for financial KG construction.
method Agentic and holistic evaluation principles, deterministic commit-then-justify judging protocol, binary and ordinal evaluations.
result Reflection-based extraction outperforms single-pass extraction in comprehensiveness, precision, and relevance.