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.

168,742 papers · 148 categories

Trend · papers per month

7132026 · May 202619922001200920172026
48 results for Soft Best-of-N

Improved inference-time alignment using Best-of-N and smoothing.

problem Reward overoptimization in Best-of-N (BoN) due to poor proxy reward models.
method Introduced Soft Best-of-N (SBoN) and analyzed its performance through KL divergence and regret analysis.
result Smoothing helps SBoN mitigate reward overoptimization, especially when proxy reward quality is low.

The abstract explores connections between reinforcement learning, scaling, and diffusion.

problem Aligning reinforcement learning with human feedback and scaling techniques.
method Clarifying connections between reinforcement learning, scaling, and diffusion.
result Introducing a resampling approach for alignment and reward-directed diffusion models.

Best-of-N sampling reveals reward targets from preference data, influencing N and base distribution choices.

problem Understanding reward extraction from Best-of-N preference data and optimal N and base distribution choices.
method Specialized analysis of preference data via induced conditional distribution, deriving reward targets and design principles.
result Reward targets are explicit functions of N and base distribution, and bounded-class minimizers approach these targets as N grows.

Two methods for model adaptation compared; fine-tuning outperforms Best-of-N in realizable settings.

problem Comparing methods for adapting large language models to new tasks.
method Supervised fine-tuning vs. Best-of-N approach.
result Supervised fine-tuning outperforms Best-of-N in realizable settings.

New method optimizes language model performance for test-time strategies.

problem Mismatch between training objectives and test-time deployment of large language models.
method Tail-Extrapolated estimators to approximate best-of-N performance from limited training rollouts.
result Improved performance of best-of-N deployment across various models and datasets.

Faster WIND accelerates iterative BOND for LLM alignment.

problem Iterative BOND is inefficient in practice due to sample and computation inefficiency.
method Unified game-theoretic connection to self-play alignment, WIND framework with efficient algorithms.
result WIND variant achieves superior sample efficiency and faster computation.

SWIFT learns intrinsic rewards from LLM hidden states for efficient best-of-N sampling.

problem Efficiency and scalability of reward models for LLMs.
method SWIFT (Simple Weighted Intrinsic Feedback Technique) learns a reward function directly from LLM hidden states.
result SWIFT outperforms existing baselines by 12.7% on MATH dataset while using less than 0.005% of their parameters.

The paper analyzes the reward improvement of aligned policies in large language models.

problem Optimizing policies in large language models while staying close to a reference policy.
method Information-theoretic analysis and reduction to exponential order statistics.
result Information-theoretic upper bounds on reward improvement are derived.

New algorithm improves inference-time alignment without reward hacking.

problem Improving quality of responses from language models with limited compute.
method Inference-time alignment, focusing on extttInferenceTimePessimism exttt{InferenceTimePessimism} algorithm.
result Optimal performance and scaling-monotonicity of extttInferenceTimePessimism exttt{InferenceTimePessimism}.

The study examines how verifier imperfections impact test-time scaling techniques.

problem Understanding how verifier imperfections affect test-time scaling methods.
method Proves the instance-level accuracy of Best-of-N and Rejection Sampling methods using the geometry of the verifier's ROC curve.
result RS outperforms BoN for fixed compute, but both converge to the same accuracy in the infinite-compute limit.

This work explores test-time scaling strategies for LLMs, improving sample efficiency and expressiveness.

problem Understanding the sample efficiency and expressiveness of test-time scaling strategies for LLMs.
method Established separation and expressiveness results for self-consistency, best-of-nn, and self-correction strategies.
result Self-correction enables Transformers to simulate online learning over multiple tasks without prior knowledge.

Employers actively look for talents having not only specific hard skills but also various soft skills. To analyze the soft skill demands on the job market, it is important to be able to detect soft skill phrases from job advertisements automatically. However, a naive matching of soft skill phrases can lead to false pos…

2018-07-20abs ↗pdf ↗

QAlign improves language model alignment with less compute, outperforming existing methods.

problem Improving language model performance with limited test-time computation.
method QAlign: sampling from optimal aligned distribution using Markov chain Monte Carlo.
result Consistent improvements over existing methods on various benchmarks.

Paper proposes a new loss function for conditional models using soft targets.

problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.

Deep model learns from labeled and unlabeled data for industrial soft sensing.

problem Lack of data limits soft sensor development in industrial processes.
method Hierarchical, generative deep latent variable model for semi-supervised multi-unit soft sensing.
result Model outperforms current methods for soft sensing in industrial processes.

Improves deep neural networks using soft labels through alternating minimization.

problem Improving deep neural networks training with soft labels.
method Co-Learns DNNs and soft labels via Alternating Minimization of two objectives.
result COLAM achieves improved performance on many tasks with better testing classification accuracy.

The paper develops a multi-unit soft sensing model for virtual flow meters that improves few-shot learning.

problem Improving soft sensor performance for new wells with limited data.
method Formulates a probabilistic, hierarchical model using a deep neural network for multi-unit soft sensing.
result Multi-unit models trained on many wells can perform well on new wells with just a few data points.

In this article supervised learning problems are solved using soft rule ensembles. We first review the importance sampling learning ensembles (ISLE) approach that is useful for generating hard rules. The soft rules are then obtained with logistic regression from the corresponding hard rules. In order to deal with the p…

2012-05-21abs ↗pdf ↗

Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpretability. As a successful unsupervised model in deep learning, the autoencoder embraces a wide spectrum of applications, yet it suffers fro…

2018-12-31abs ↗pdf ↗

Bayesian neural networks update beliefs with soft evidence, improving accuracy and calibration.

problem Updating neural network weights with uncertain or soft evidence.
method Developed two algorithms to approximate Jeffrey's rule for updating neural network weights.
result Jeffrey-based methods outperform traditional approaches in accuracy and calibration, especially in noisy data.

A method for selecting pseudo-labeled data in semi-supervised learning using generalized Bayes and soft revision.

problem Selecting pseudo-labeled data for semi-supervised learning with robustness to uncertainty.
method Using credal sets and the Gamma-Maximin method with soft revision to update priors and select pseudo-labeled data.
result The Gamma-Maximin method with soft revision can achieve promising results, especially in scenarios with low labeled data proportions.

Constructs noncommutative spaces for D-branes on complex algebraic spaces.

problem Mathematical model for D-branes on noncommutative spaces.
method Toric geometry, Azumaya schemes, invertible sheaves.
result Embeds algebraic Calabi-Yau spaces into soft noncommutative schemes.

HyperFair integrates fairness in recommender systems using probabilistic soft logic.

problem Ensuring fairness in recommender systems across diverse domains.
method Soft fairness constraints integrated as regularization in a joint inference objective function.
result HyperFair improves fairness of predictions from black-box models and hybrid systems.

Partial soft-matching distance improves neural representation comparison by allowing some neurons to remain unmatched.

problem Neural representations are noisy and contain outliers, making traditional matching methods unreliable.
method Extends soft-matching distance to a partial optimal transport setting, allowing some neurons to remain unmatched.
result Partial soft-matching provides robust correspondences that are more reliable under noise and outliers.

A framework learns dynamic soft labels to improve model generalization and accuracy.

problem Models trained on one-hot labels overfit and are sensitive to noisy annotations.
method Proposes a framework where labels are treated as learnable parameters, adapting dynamically during optimization.
result Consistent gains across different datasets and architectures, improving ResNet18 by 2.1% on CIFAR100.

New algorithms optimize a soft-robust criterion in reinforcement learning, reducing conservatism.

problem Computing robust policies for high-stakes decisions with limited data.
method Soft-robust criterion using risk measures, two algorithms for optimization.
result Our algorithms produce less conservative solutions than existing methods.