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.

168,695 papers · 148 categories

Trend · papers per month

71142213284 · Jun 202019922001200920172026
48 results for Semantic Divergence Metrics

Paper introduces SDM for detecting LLM hallucinations, improving on entropy tests.

problem Challenges of Large Language Models (LLMs) with non-factual, nonsensical responses.
method Joint clustering on sentence embeddings to measure semantic divergence between prompts and responses.
result SDM framework detects deeper form of arbitrariness in LLM responses.

Two new metrics assess LLM faithfulness and entropy, improving model reliability.

problem Evaluating the accuracy of LLMs in generating coherent responses.
method Proposes SF and SEP metrics based on information theory and thermodynamics.
result High SF and SEP scores indicate more faithful LLM responses.

SHAP Distance assesses semantic fidelity of synthetic tabular data.

problem Semantic fidelity of synthetic tabular data is not well evaluated.
method SHAP Distance, defined as cosine distance between global SHAP attribution vectors.
result SHAP Distance detects semantic discrepancies overlooked by standard measures.

New method identifies shared topics in LLM inputs and outputs for better detection of hallucinations.

problem Detecting semantic drift in LLM responses from context.
method Transformed Deterministic Information Bottleneck (DIB) into UDIB for high-dimensional data.
result UDIB generates more informative topic representations for SDM, improving hallucination detection.

A new method for image translation using disentangled style and content preservation.

problem Difficulty in maintaining original content during reverse diffusion in diffusion-based image translation.
method Disentangled style and content representation using intermediate keys from ViT model, CLIP loss, semantic divergence loss, and resampling strategy.
result Outperforms state-of-the-art models in text-guided and image-guided translation tasks.

A new framework evaluates LLM calibration in open-ended QA.

problem Evaluating LLM calibration in open-ended QA settings.
method Sem-ECE framework: sampling answers, grouping by semantic classes, and using frequencies as confidence.
result Sem-ECE estimators are unbiased and Sem2_2 achieves smaller calibration error.

New framework using Jensen-Shannon divergence improves domain adaptation theory.

problem Incoherence between empirical domain adversarial training and theoretical H\mathcal{H}-divergence.
method Established new theoretical framework based on Jensen-Shannon divergence, derived bi-directional upper bounds.
result Framework exhibits flexibilities for various transfer learning problems.

Sparse Transformers degrade semantic information first, with early layers encoding more.

problem Understanding how sparse Transformers affect learned representations and semantic information.
method Probed Transformers with progressively pruned weights to observe changes in semantic information and model behavior.
result Complex semantic information is first to degrade in sparse Transformers, with early layers encoding more.

Proposes RDASS for better Korean text summarization evaluation.

problem ROUGE scores fail to capture semantic meaning in Korean text summarization.
method Introduces RDASS metrics and a method to improve their correlation with human judgment.
result RDASS metrics correlate better with human judgment than ROUGE scores.

Develops a new divergence framework that combines ff-divergences and IPMs.

problem Comparing distributions that are not absolutely continuous.
method Introduces (f,Γ)(f,Γ)-divergences as a two-stage mass-redistribution/mass-transport process.
result Improves estimation, learning, and uncertainty quantification in GANs for heavy-tailed distributions.

Unified view of KL-divergence and IPMs via DRE, with new DRM metrics.

problem Unified understanding of KL-divergence and IPMs.
method Unified representation via maximum likelihood density-ratio estimation (DRE).
result Unified form of IPMs and novel DRM metrics.

SOM-VQ tokenizes discrete models with semantic structure and navigable topology.

problem Lack of semantic structure in vector quantized representations limits interpretable human control.
method Combines vector quantization with Self-Organizing Maps to learn discrete codebooks with explicit topology.
result SOM-VQ produces more learnable token sequences and provides an explicit navigable geometry in code space.

Continuous vector representations of words and objects appear to carry surprisingly rich semantic content. In this paper, we advance both the conceptual and theoretical understanding of word embeddings in three ways. First, we ground embeddings in semantic spaces studied in cognitive-psychometric literature and introdu…

2015-09-18abs ↗pdf ↗

Replicated Softmax model, a well-known undirected topic model, is powerful in extracting semantic representations of documents. Traditional learning strategies such as Contrastive Divergence are very inefficient. This paper provides a novel estimator to speed up the learning based on Noise Contrastive Estimate, extende…

2015-06-24abs ↗pdf ↗

The paper explores statistical and topological properties of sliced probability divergences.

problem Understanding the topological, statistical, and computational consequences of slicing divergences.
method Deriving theoretical properties of sliced probability divergences, including metric axioms preservation and weak continuity.
result Sliced divergences share similar topological properties and have stable sample complexity.

This thesis bridges Lie theory and sketch theory using tangent categories.

problem Two diverging lines of research in Lie theory.
method Developing involution algebroids and using tangent categories to connect Lie algebroids and Weil algebras.
result The category of Lie algebroids is a functor category, and the Lie functor is a composition with a tangent categorical functor.

DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints bet…

2017-03-21abs ↗pdf ↗

Bregman divergences generalize measures such as the squared Euclidean distance and the KL divergence, and arise throughout many areas of machine learning. In this paper, we focus on the problem of approximating an arbitrary Bregman divergence from supervision, and we provide a well-principled approach to analyzing such…

2019-05-28abs ↗pdf ↗

Protocol for constructing tailored evaluation datasets for semantic models.

problem Evaluation of domain-specific semantic models, focusing on top ranks.
method Adaptive pairwise comparisons, relatedness-based evaluation dataset, metrics, stochastic transitivity model.
result Effectiveness of the proposed dataset construction protocol confirmed.

Study on 3D Lie groups finds all generalized Einstein metrics.

problem Classifying generalized Einstein metrics on 3D Lie groups.
method Developed theory of left-invariant generalized pseudo-Riemannian metrics, computed Ricci tensor, determined all metrics.
result Determined all generalized Einstein metrics on three-dimensional Lie groups.

A new method uncovers intrinsic data structures for unsupervised domain adaptation.

problem Learning domain-aligned features can damage intrinsic target discrimination.
method Structurally Regularized Deep Clustering (H-SRDC) integrating structural source regularization.
result H-SRDC outperforms existing methods in image classification and semantic segmentation.

New framework detects near vs. far out-of-distribution samples for AI safety.

problem Binary OOD detection fails to distinguish between semantically close and distant unknown risks.
method Ternary classification based on Low-Entropy Semantic Manifolds and Semantic Surprise Vector.
result Framework achieves state-of-the-art performance on ternary OOD detection task.

We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model. Both the generative and inference model are trained using the adversarial learning paradigm. We demonstrate that the hierarchical structure supports the learning of progressively more abstract represe…

2018-02-04abs ↗pdf ↗

Paper explores how text generation quality and diversity metrics relate to distribution fitting.

problem Unclear relation between text generation quality and diversity metrics and distribution fitting.
method Theoretical approach to prove a linear combination of quality and diversity metrics can be a divergence metric.
result CR/NRR proposed as a better substitute for BLEU/Self-BLEU metrics.

New insights show embedding lengths correlate with semantic properties.

problem Contrastive embedding norms ignore embedding magnitudes but correlate with semantic properties.
method Formal theoretical framework and analysis of optimization dynamics.
result Embedding lengths encode semantic information as a byproduct of training.

New method makes quality metrics scale-invariant for high-dimensional data.

problem Scale sensitivity in quality metrics affects the accuracy of data projections.
method Analytical and empirical investigation of stress and KL divergence; introduction of a scale-invariant technique.
result The proposed technique accurately captures expected behavior and makes metrics scale-invariant.

Improved genetic programming by optimizing mutation operators for continuous program search.

problem Small syntactic mutations in genetic programming can lead to unpredictable behavioral shifts.
method Learned a compact trading-strategy DSL, created a block-factorized embedding, and designed geometry-compiled mutation operators.
result Geometry-compiled mutation operators discover strong strategies using fewer evaluations and achieve higher Sharpe ratios.

Active learning selects high-quality examples for text-to-SQL systems.

problem Efficiently annotate large language models for text-to-SQL systems.
method Formalizes example selection as a constrained experimental design problem over semantic query embeddings, proposing a stratified greedy algorithm that maximizes heteroscedastic mutual information.
result Proposed method significantly reduces labeling effort while maintaining high text-to-SQL retrieval accuracy.

A commonly used evaluation metric for text-to-image synthesis is the Inception score (IS) \cite{inceptionscore}, which has been shown to be a quality metric that correlates well with human judgment. However, IS does not reveal properties of the generated images indicating the ability of a text-to-image synthesis method…

2019-10-31abs ↗pdf ↗

New rigidity results for quasi-Einstein metrics with non-zero divergence-free vector fields.

problem Classifying quasi-Einstein metrics with specific vector field properties.
method Analyzing quasi-Einstein metrics on closed manifolds and near-horizon geometries of extreme black holes.
result These metrics always admit a one-parameter group of isometries generated by the divergence-free vector field.