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.

168,657 papers · 148 categories

Trend · papers per month

4386128171 · May 202619922001200920172026
48 results for mathematical language

Self-supervised skip-tree training improves mathematical reasoning in language models.

problem Improving logical reasoning in language models for formal mathematics.
method Self-supervised language modeling on mathematical formulas, skip-tree task.
result Models trained on skip-tree task outperform standard models in mathematical reasoning tasks.

Transformer models can solve complex math problems with less data.

problem Solving complex symbolic mathematics problems with limited data.
method Pretrain transformer models on language translation tasks and fine-tune for symbolic math.
result Pretrained transformer models achieve comparable accuracy to state-of-the-art models with less data.

Language models help text classification tasks by predicting next words.

problem Lack of theoretical understanding of why language models perform well on downstream tasks.
method Mathematical study of the connection between next word prediction and text classification, formalizing it and quantifying the benefit.
result Language models that are ε-optimal in cross-entropy learn features that can solve classification tasks with linear approximation.

Mathematical framework for language models processes text and predicts next tokens.

problem Understanding and optimizing the performance of large language models.
method Describes encoding, prediction models, learning from data, and deployment of LLMs.
result Demonstrates remarkable empirical successes and provides a platform for further research.

The paper applies math and physics to language models, introducing entropy and geometric concepts.

problem Understanding and improving language models to approximate intelligent language.
method Formal definitions, functional analysis, topology, thermodynamics, and set theory.
result Entropy function reveals key obstacles for LLMs and offers insights into language models.

These notes grew out of a lecture course on mathematical methods of classical physics for students of mathematics and mathematical physics at the master's level. Also, physicists with a strong interest in mathematics may find this text useful as a resource complementary to existing textbooks on classical physics. Topic…

2016-12-09abs ↗pdf ↗

Method guarantees coherent factuality for language model outputs in reasoning tasks.

problem Ensuring correctness of language model outputs in reasoning tasks.
method Developed a conformal-prediction-based method applied to subgraphs within a deducibility graph.
result Achieved coherent factuality across target coverage levels, 90% on stricter definition.

The paper explains how language models acquire complex skills through scaling laws and statistical analysis.

problem Understanding how language models acquire new skills as their size and training data increase.
method Statistical framework and mathematical analysis of scaling laws.
result Language models can learn complex skills efficiently due to a strong inductive bias.

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.

This article investigates a new gauge theoretic approach to Einstein's equations in dimension 4. Whilst aspects of the formalism are already explained in various places in the mathematics and physics literature, our first goal is to give a single coherent account of the theory in purely mathematical language. We then e…

2013-12-10abs ↗pdf ↗

We develop a statistical framework to benchmark and select large language models based on their risks.

problem Benchmarking and selecting large language models based on their associated risks.
method A distributional framework using first and second order stochastic dominance, linked to mean-risk models in finance.
result Formalizes a risk-aware approach for model selection, balancing risk and utility.

In this note we review the basic mathematical ideas used in finance in the language of modern physics. We focus on discrete time formalism, derive path integral and Green's function formulas for pricing. We also discuss various risk mitigation methods.

2020-01-26abs ↗pdf ↗

The study uncovers latent capabilities of language models via causal representation learning.

problem Rigorous causal evaluations of language model capabilities are challenging due to confounding effects and computational costs.
method Proposes a causal representation learning framework to identify latent capability factors as causally interrelated after controlling for a common confounder (base model).
result Identifies a three-node linear causal structure explaining performance variations across 1500 models and six benchmarks.

Enhances math problem-solving models with multi-turn preference learning.

problem Improving mathematical problem-solving capabilities of large language models.
method Introduces a multi-turn direct preference learning framework for tool-integrated mathematical reasoning tasks.
result Significant performance improvements in model accuracy on math datasets.

Study quantifies how LLMs capture higher-order statistical structure using cumulant expansion.

problem Understanding how LLMs internalize statistical structure during next-token prediction.
method Cumulant-expansion framework treating softmax entropy as perturbation around center distribution.
result Cumulants reveal distinct signatures for mathematical vs. general text prompts, quantifying feature-learning dynamics.

Galactica learns from scientific literature to help researchers.

problem Information overload in scientific literature makes it hard to find useful insights.
method Trained on a large corpus of scientific papers, reference material, and knowledge bases.
result Outperforms existing models on various scientific tasks, including LaTeX equations and mathematical reasoning.

iPrompt uses LLMs to generate natural-language explanations of data patterns.

problem Finding and explaining patterns in data using natural language.
method Interpretable autoprompting (iPrompt) that generates natural-language explanations based on LLMs.
result iPrompt can accurately find and explain data patterns, improving upon human-written prompts.

DOS improves language model generation by considering inter-token dependencies.

problem Lack of sequence-level information and inter-token dependencies in existing decoding strategies.
method Dependency-Oriented Sampler (DOS) that uses attention matrices to approximate inter-token dependencies.
result DOS consistently achieves superior performance on code generation and mathematical reasoning tasks.

Unified SVD compression fails in practical tasks, highlighting the importance of per layer activation reconstruction.

problem The failure of a unified SVD compression method in practical tasks like perplexity and accuracy.
method Unified optimization problem for SVD based compression methods, focusing on cross-layer coupling.
result Downstream metrics like perplexity and accuracy degrade severely compared to standard per layer SVD LLM.

Hamiltonian Monte Carlo (HMC) is arguably the dominant statistical inference algorithm used in most popular "first-order differentiable" Probabilistic Programming Languages (PPLs). However, the fact that HMC uses derivative information causes complications when the target distribution is non-differentiable with respect…

2018-04-07abs ↗pdf ↗

This work offers a broad perspective on probabilistic modeling and inference in light of recent advances in probabilistic programming, in which models are formally expressed in Turing-complete programming languages. We consider a typical workflow and how probabilistic programming languages can help to automate this wor…

2018-10-02abs ↗pdf ↗

In this paper, we address the task of Optical Character Recognition(OCR) for the Telugu script. We present an end-to-end framework that segments the text image, classifies the characters and extracts lines using a language model. The segmentation is based on mathematical morphology. The classification module, which is …

2015-09-20abs ↗pdf ↗

The sequence (xn)nN=(2,5,15,51,187,)(x_n)_{n\in\mathbb N} = (2,5,15,51,187,\dots) given by the rule xn=(2n+1)(2n1+1)/3x_n=(2^n+1)(2^{n-1}+1)/3 appears in several seemingly unrelated areas of mathematics. For example, xnx_n is the density of a language of words of length nn with four different letters. It is also the cardinality of the quotient of $(\math…

2014-09-06abs ↗pdf ↗

This paper compares self-reflection and budget tuning for LLMs, revealing domain-specific performance gains.

problem Improving inference-time performance of LLMs without retraining, balancing quality, cost, and latency.
method Systematic comparison of self-reflection and budget tuning across mathematical reasoning and translation tasks, evaluating various LLMs and model families.
result Substantial domain-dependent variation in self-reflection effectiveness, with up to 220% performance gains in mathematical reasoning.

This paper introduces a gradient analysis framework to improve language model performance by rewarding good examples and penalizing bad ones.

problem Improving language model output quality by penalizing bad examples.
method Gradient analysis of loss functions to reward good examples and penalize bad ones.
result ExMATE is superior to MLE and combining DPO with ExMATE enhances performance.

Neural network language models (NNLMs) have achieved ever-improving accuracy due to more sophisticated architectures and increasing amounts of training data. However, the inductive bias of these models (formed by the distributional hypothesis of language), while ideally suited to modeling most running text, results in …

2019-12-11abs ↗pdf ↗

DKPS provides guarantees for synthetic data from Transformer models, improving downstream tasks.

problem Lack of labeled data for building performant AI models.
method Data Kernel Perspective Space (DKPS) for mathematical analysis of synthetic data quality.
result Concrete statistical guarantees for the quality of transformer model outputs.

AER dynamically adjusts entropy regularization for better LLM reinforcement learning.

problem Policy entropy collapse in RLVR training limits exploration and reasoning performance.
method Adaptive Entropy Regularization (AER) with difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.
result AER consistently outperforms baselines on mathematical reasoning benchmarks, improving both accuracy and exploration.