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

55111166221 · Jun 202019922001200920172026
48 results for LLM text detection

LLmFPCA-detect detects anomalies in sparse longitudinal text data using LLMs and mFPCA.

problem Challenges in detecting patterns and anomalies in sparse longitudinal textual data.
method Pairs LLM-based text embeddings with mFPCA to detect clusters and anomalies.
result LLmFPCA-detect outperforms state-of-the-art baselines on Amazon and Wikipedia datasets.

Adaptive testing segments watermarked text from LLMs.

problem Distinguishing LLM-generated text from human-written content.
method Generalized likelihood-based detection method adapted to inverse transform sampling, removing prompt estimation sensitivity.
result Effective and robust method for segmenting watermarked text.

Paper introduces a statistical framework for watermarking LLM-generated text.

problem Detecting LLM-generated text from human-written text with statistical signals.
method Hypothesis testing formulation, pivotal statistic selection, secret key, closed-form expression of false negative rate, minimax optimization.
result Derives optimal detection rules for LLM-generated text, demonstrating higher power than existing methods.

AdaDetectGPT improves text authorship detection with statistical guarantees.

problem Determining if text is authored by a human or an LLM.
method Adaptive learning of a witness function from training data to enhance logits-based detectors.
result AdaDetectGPT nearly uniformly improves text authorship detection, with up to 37% improvement.

Enhanced regime shifts detection using unstructured text and financial data.

problem Detecting regime shifts in financial markets is challenging due to noisy and multicollinear data.
method Combines LLM reasoning on unstructured text and statistical validation on financial time series.
result Framework achieves F1 score of 0.82, outperforming pure data-driven methods.

The paper develops a method to identify LLM-generated text without training.

problem Identifying LLM-generated text among human-generated content.
method Modeling LLM text as a sequential process and designing zero-shot statistical tests.
result The method can distinguish between text from known LLMs and non-sanctioned models with low false positive rates.

Estimates watermarked content proportions in mixed-source texts.

problem Optimally estimating the proportion of watermarked content in texts with mixed sources.
method Casting the problem as estimating a proportion parameter in a mixture model based on pivotal statistics.
result Proposes efficient estimators for watermark proportion and shows their accuracy through evaluations.

LLMs' explanations are often insufficient and vary with input distribution.

problem Evaluating the sufficiency of LLM explanations without predefined biases.
method Generalizing sufficiency to arbitrary explanations, using LLM's input beliefs, and introducing SCSuff metric.
result Explanation sufficiency can vary with input distribution and is weakly correlated with model size, accuracy, or output entropy.

Paper proposes using online text data to predict CPI with LLMs.

problem Forecasting Consumer Price Index (CPI) using low-frequency survey-based data.
method Develops an LLM-based approach combining online text time series with monthly CPI data.
result Establishes the asymptotic properties and provides prediction intervals for CPI forecasts.

New framework improves text watermark detection under imperfect pseudorandomness.

problem Structured dependence in generated text from language models causes Type I error control issues.
method Hierarchical two-layer partition, minimal units, non-asymptotic efficiency measure, minimax hypothesis testing.
result Closed-form optimal rules for watermark detection under imperfect pseudorandomness.

Text clustering method replaces centroids with summaries for interpretability and scalability.

problem Efficiently clustering text data while maintaining interpretability and scalability.
method k-NLPmeans and k-LLMmeans, which periodically replace numeric centroids with textual summaries.
result Consistently outperforms classical baselines and recent LLM-based clustering methods.

This paper improves retrieval for LLMs in financial document Q&A.

problem Suboptimal text chunk retrieval by RAG causes inaccuracies in LLM responses.
method Sophisticated chunking techniques, query expansion, metadata annotations, re-ranking algorithms, and embedding fine-tuning.
result Enhanced retrieval quality improves LLM performance and reliability.

Study evaluates if LLMs have company-specific biases in financial sentiment analysis.

problem Evaluating if large language models exhibit company-specific biases in financial sentiment analysis.
method Comparing sentiment scores with and without company names, constructing economic models, and empirical analysis.
result LLMs show company-specific biases in sentiment analysis, impacting investor behavior and stock prices.

This paper fine-tunes LLMs for stock return prediction using financial news.

problem Improving stock return forecasting accuracy using LLMs.
method Fine-tuning LLMs with text and forecasting modules, comparing encoder-only and decoder-only models, and integrating token-level representations.
result LLMs' aggregated token-level embeddings enhance return predictions for long-only and long-short portfolios.

Paper proposes CLAIR for efficient LLM fine-tuning across clients.

problem Fine-tuning large language models (LLMs) efficiently and collaboratively.
method Federated LoRA fine-tuning with Collaborative Low-rank Alignment and Identifiable Recovery (CLAIR).
result CLAIR achieves better performance and contamination detection compared to local fine-tuning.

FinDKG uses LLMs to detect financial trends from news articles.

problem Detecting global financial trends from unstructured text data.
method Fine-tuned LLMs for generating DKGs, KGTransformer for analysis.
result KGTransformer outperforms existing thematic ETFs in financial thematic investing.

LFD method improves text classification by making features clearer and less label-leaking.

problem Creating interpretable text representations that are both predictive and understandable.
method LFD method: proposes lexical and semantic features from contrastive text pairs, screens candidates using κκ, and selects features by residual gain.
result LFD features achieve higher human-human and human-LLM agreement than baseline concepts and are less label-leaking.

BioFinBERT analyzes sentiment of biotech press releases and financial text around inflection points.

problem Analyzing sentiment of biotech press releases and financial text around inflection points.
method Finetuning BioBERT on financial datasets to create BioFinBERT for sentiment analysis.
result BioFinBERT accurately analyzes sentiment of biotech press releases and financial text around inflection points.

Improved text-conditioned regression using LLMs and diffusion-based neural processes.

problem Major error cascades and computational inefficiency in LLMs for short sequences.
method Combining LLM predictive densities with a diffusion-based neural process.
result Better-calibrated predictions and locally consistent trajectories.

LLMs encode latent topic distributions, suggesting Bayesian inference.

problem Capturing topic structure from large language models.
method Connecting LLM optimization to implicit Bayesian inference and de Finetti's theorem.
result LLMs recover latent topic distributions, matching LDA-generated topics.

Embed-KCPD segments text without labels, outperforming baselines.

problem Unsupervised text segmentation is challenging due to lack of boundary labels.
method Embed-KCPD represents sentences as embeddings and estimates boundaries via penalized KCPD.
result Embed-KCPD outperforms strong unsupervised baselines across benchmarks.

BTZSC benchmarks zero-shot text classification across diverse models.

problem Systematically comparing zero-shot text classification across various models.
method Comprehensive benchmark of 22 datasets, comparing NLI cross-encoders, embedding models, rerankers, and instruction-tuned LLMs.
result Rerankers and instruction-tuned LLMs outperform NLI cross-encoders, with rerankers setting a new state-of-the-art.

Shorter adversarial prompts help protect LLMs from jailbreak attacks.

problem Protecting large language models from jailbreak attacks with long adversarial suffixes.
method Adversarial training on shorter adversarial suffixes to defend against longer adversarial suffixes.
result Aligning LLMs on shorter adversarial suffixes can effectively defend against jailbreak attacks with longer suffixes.

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.

Study evaluates consistency of LLMs in binary text classification, providing systematic guidance.

problem Lack of reliable methods for evaluating large language model (LLM) binary text classification.
method Adapting psychometric principles, the study determines sample size requirements, develops metrics for invalid responses, and evaluates intra- and inter-rater reliability.
result LLMs demonstrated high intra-rater consistency, achieving perfect agreement on 90-98% of examples, with smaller models outperforming larger counterparts.

FinGPT democratizes financial data for LLMs, enabling innovation.

problem Limited financial text datasets and disparities between general and financial text data.
method Automates collection and curation of real-time financial data from diverse Internet sources, fine-tuning with RLSP and LoRA.
result Democratizes access to financial data for LLMs, enabling innovation.

Estimates proportions of LLM-generated text in mixed documents.

problem Estimating the proportion of text generated by a pre-specified LLM in mixed documents.
method Developed estimators for two observation regimes: full observation and pivotal reduction, and established sample complexity bounds.
result Full observation estimators require fewer samples than pivotal reduction estimators.