Research
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.

169,051 papers · 148 categories

Trend · papers per month

6.2%12.4%18.6%24.7% · Feb 202619922001200920182026
48 results for rubric sampling

Paper tackles zero-shot code feedback using rubric sampling with deep learning.

problem Lack of historical data for supervised learning in introductory programming assignments.
method Human-in-the-loop rubric sampling with deep learning inference.
result Autonomous feedback for first students is more accurate than data-hungry algorithms and approaches human level fidelity.

FinanceHarness automates financial deep research with specialized tools and benchmarks.

problem Lack of specialized financial deep research for financial analysis.
method FinanceHarness uses a layered harness and FinanceGym for specialized research questions and validation.
result FinanceHarness improves rubric scores by 7.1% and achieves 82% pass rate with expert validation.

Bayesian active learning improves holistic educational assessments.

problem Gap between holistic CJ and criterion-based rubrics in education.
method Extends Bayesian CJ to handle multiple LO components, using entropy-based active learning.
result Enhanced predictive rankings with uncertainty estimates and quantified assessor agreement.

The paper proposes a rubric and incentives to prevent peer review from becoming a 'tragedy of the commons'.

problem The growth of machine learning threatens the sustainability of peer review.
method Proposes a rubric for objective review quality and financial compensation for reviewers.
result Avoiding a 'tragedy of the commons' outcome in peer review.

IPO Finance Agent extends Finance Agent v2 for SpaceX S-1 filings, improving accuracy and cost-efficiency.

problem Evaluating IPO due diligence tasks with long-form documents.
method Extended task domain, improved agentic harness with contextual retrieval, automated rubric generation.
result Best-performing model reaches 79.8% accuracy, cost-efficient model at 77.2% with 0.05 USD per query.

ValueBlindBench tests LLM-generated investment rationales for validity before returns are known.

problem Delayed-ground-truth evaluation of LLM-generated investment rationales.
method Agreement-gated stress testing protocol to validate LLM-judged rationales.
result ValueBlindBench prevents overclaims and identifies flawed financial constructs.

IPO Finance Agent evaluates LLMs on SpaceX IPO due diligence, surpassing Finance Agent v2.

problem Evaluating language models on financial tasks like IPO due diligence.
method Introducing IPO Finance Agent and an evaluator-optimizer pipeline.
result The best-performing model reaches 79.4% accuracy at 0.30 USD per query.

Inference-Time Scaling can be extended to domains prone to systematic failure using intrinsic statistics.

problem Scaling inference time in domains prone to systematic failure
method Intrinsic Selection (iS), Intrinsic Particle Filtering (iPF), and Particle Distillation (dPF)
result Intrinsic Selection improves engineering design selection by 20% and pass@1 by 6.1 points on average.

We consider the quantifier-free languages, Bc and Bc0, obtained by augmenting the signature of Boolean algebras with a unary predicate representing, respectively, the property of being connected, and the property of having a connected interior. These languages are interpreted over the regular closed sets of n-dimension…

2011-10-18abs ↗pdf ↗

CausalGame benchmarks LLM agents' causal thinking in games.

problem Evaluating causal thinking in AI Scientists with LLMs.
method Interactive games with 14 scenarios incorporating selection bias, measurement error, and hidden confounders.
result None of the 30 LLM agents demonstrated reliable causal thinking, with the best model achieving only 68.0% survival.

Develops tools to decompose spurious variations in causal models.

problem Understanding and decomposing spurious variations in causal relationships.
method Formal tools for decomposing spurious effects in Markovian and Semi-Markovian models.
result First results on non-parametric decomposition of spurious effects and sufficient conditions for identification.

Benchmark assesses LLMs' causal inference skills, revealing significant limitations.

problem Lack of rigorous evaluation of LLMs' causal inference capabilities.
method CausalPitfalls benchmark with structured challenges and grading rubrics.
result Significant limitations in current LLMs' statistical causal inference.

Meta-Router optimizes LLM selection using gold-standard and preference-based data.

problem Training a high-quality LLM router with combined data sources is challenging due to bias and scarcity.
method Developed an integrative causal router training framework to correct bias and improve routing accuracy.
result Our approach delivers more accurate routing and improves the trade-off between cost and quality.

Benchmark tests LLMs on discovering physics laws in unconventional worlds.

problem Difficulties in distinguishing genuine reasoning from recall in LLMs across physics evaluations.
method Interactive benchmark with 22 worlds governed by various unconventional physics laws, requiring agents to design experiments and revise hypotheses.
result Strongest agents fail on worlds requiring latent structure discovery, highlighting limitations in long-term reasoning.

Unified approach to path planning using probabilistic inference on factor graphs.

problem Path planning problems using probabilistic inference.
method Unified framework using probabilistic factor graphs and message composition rules.
result Unified approach includes various algorithms like Sum-product, Max-product, Dynamic programming, and mixed criteria.

Enhanced Sampling Scheme improves masked generative modeling.

problem Limitations of existing sampling schemes in masked non-autoregressive generative modeling.
method ESS consists of three stages: Naive Iterative Decoding, Critical Reverse Sampling, and Critical Resampling.
result ESS achieves significant performance gains in unconditional and class-conditional sampling.

This paper reviews various sampling methods from statistics and machine learning.

problem Addressing sampling methods in statistics and machine learning.
method Explains and reviews simple random sampling, bootstrapping, stratified sampling, cluster sampling, multistage sampling, network sampling, snowball sampling, and sampling from cumulative distribution function.
result Summarizes characteristics, pros, and cons of different sampling methods.

RISA improves VFL by using imputed samples with low uncertainty.

problem Limited overlapping samples constrain VFL performance.
method Imputing non-overlapping samples and using evidence theory to select reliable imputed samples.
result Significant performance gains achieved, especially with limited overlapping samples.

Improved privacy-preserving methods for estimating multiple samples from distributions.

problem Estimating multiple samples from distributions while maintaining privacy.
method Developed new multi-sampling techniques for differentially private data estimation.
result Achieved significant reduction in sample complexity for multi-sampling from finite domains and Gaussian distributions.

Paper introduces a new sampling method combining Consistency Models with importance sampling.

problem Inherent errors in samples and high NFEs for high-quality samples in Boltzmann distributions.
method Combines Consistency Models with importance sampling to produce unbiased samples with minimal NFEs.
result Produces unbiased samples using only 6-25 NFEs, comparable to 100 NFEs for DDPMs.

Wedge Sampling improves tensor completion with nearly-linear sample complexity.

problem Efficiently completing low-rank tensors from a subset of entries.
method Non-adaptive wedge sampling to promote structured connections in tensor completion.
result Polynomial-time algorithms achieve weak and exact recovery with nearly linear sample complexity.

Neural network accuracy improves with denser training samples.

problem Improving neural network accuracy on unseen test samples.
method Bounding empirical training error smoothed across activation regions and using it to discard high-risk test samples.
result Discarding high-risk test samples based on error bounds improves prediction accuracy by up to 20%.

Sampling is a fundamental problem in computer science and statistics. However, for a given task and stream, it is often not possible to choose good sampling probabilities in advance. We derive a general framework for adaptively changing the sampling probabilities via a collection of thresholds.In general, adaptive samp…

2017-08-16abs ↗pdf ↗

Efficiently samples sequences without replacement for machine learning models.

problem Generating diverse outputs from sequential models without duplicates.
method Incremental sampling procedure for randomized programs, including neural models.
result Efficacy and flexibility of incremental sampling for large output spaces.

Optimizes biomolecular simulations by ranking adaptive sampling policies.

problem Efficiently sampling biomolecular systems to capture complex dynamical behaviors.
method Metric-driven ranking of adaptive sampling policies to identify the optimal policy for each round.
result Different adaptive sampling policies lead to faster convergence and improved sampling performance.

Optimizes sample and round complexity in adaptive sampling from multiple distributions.

problem Adaptive sampling from multiple distributions with limited rounds and samples.
method Introduces OODS framework and analyzes tradeoffs between sample and round complexity.
result Achieves near-optimal sample complexity and sub-polynomial round complexity.

Self-adversarial learning improves Bayesian sampling efficiency and quality.

problem Highly correlated and inefficient samples from scalable Bayesian sampling methods.
method Proposes a self-adversarial learning framework to learn a conditional generator.
result Efficiently generated samples that progressively approach a target distribution.

REP-GAN improves GANs by reparameterizing proposals for better sample quality and efficiency.

problem Poor sample efficiency in GANs due to independent proposal sampling.
method REParameterizing Markov chains into the latent space of the generator to create dependent proposals.
result Empirically shows significant improvement in sample efficiency and quality.

Unified framework for model-based RL with sample complexity guarantees.

problem Designing efficient posterior sampling methods for model-based RL.
method Optimistic posterior sampling, Hellinger distance reduction, data likelihood measurement.
result Unified algorithms with state-of-the-art sample complexity guarantees.

Adversarial Sampling improves active learning by generating high entropy synthetic samples.

problem Improving active learning performance through better sample selection.
method Generative Adversarial Network (GAN) based approach to generate high entropy synthetic samples, then select similar real samples for training.
result ASAL outperforms random sample selection and other active learning methods across multiple datasets.

Proposes a neural network method to combine nonprobability and probability survey samples.

problem Combining nonprobability and probability survey samples for accurate population mean estimation.
method Uses a deep neural network to estimate sampling scores from nonprobability samples and combines them with probability sample information.
result Proposed estimators improve robustness to parametric propensity-score misspecification, especially for nonlinear selection mechanisms.

Dynamic Influence Tracker measures changing sample importance during model training.

problem Static influence measurements during training overlook how sample importance varies over time.
method Dynamic Influence Tracker (DIT) captures time-varying sample influence across arbitrary time windows.
result DIT reveals distinct learning phases with shifting priorities and detects corrupted samples more efficiently.

Optimized sampling scheme for compressed sensing combining randomness and determinism.

problem Improving compressed sensing performance with deterministic sampling.
method Optimized sampling scheme combining random and deterministic selection of rows.
result Measurable improvements in image compressed sensing for generative and sparse priors.

Predictive sampling improves on Thompson sampling for non-stationary bandit environments.

problem Thompson sampling fails in non-stationary bandit environments.
method Proposes predictive sampling, which deprioritizes actions based on information loss rate.
result Predictive sampling outperforms Thompson sampling in all tested non-stationary environments.