Telescope detects LLM generated text by measuring token repetition probability.
problem Distinguishing LLM generated text from human writing.
method Telescope Perplexity, evaluating token repetition probability.
result Telescope Perplexity enables effective zero-shot LLM detection.
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.
Paper introduces a new algorithm to detect LLM-generated text.
problem Detecting LLM-generated text to prevent misinformation.
method Adaptively learns the distance between original and rewritten text.
result Empirically, the new algorithm outperforms existing methods in most scenarios.
Classifier detects LLM-generated text with guarantees.
problem Detecting fake LLM-generated text to prevent misuse.
method Trained classifier without auxiliary info, distinguishing human and LLM text.
result Achieves higher accuracy than existing detectors with type-I error control.
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.
Paper proposes a data augmentation method for LLM-generated data in market research.
problem Bias in LLM-generated data in market research.
method Statistical data augmentation approach integrating LLM-generated and real data.
result Statistically robust estimators with reduced bias and cost savings.
ASK-NN detects distribution drifts in LLM-generated text.
problem Hallucinations and artificial text in LLM-generated outputs.
method Asymmetric two-sample test based on directed k-nearest-neighbor graph.
result ASK-NN is competitive with baselines on various benchmarks.
New method detects watermarks in LLM-generated text with human edits.
problem Dilution of watermark signals by human edits on LLM-generated text.
method Truncated goodness-of-fit test (Tr-GoF) for robust detection.
result Tr-GoF achieves optimality in robust detection of Gumbel-max watermark.
AEALT uses autoencoders to reduce text embedding dimensions for improved efficiency.
problem High dimensionality of text embeddings hinders downstream tasks.
method Factor-augmented supervised learning with autoencoders.
result AEALT outperforms conventional deep-learning approaches.
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.
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.
Method detects if text is generated by a language model with watermarks.
problem Detecting if text is generated by a language model with watermarks.
method Randomization tests and change point detection techniques.
result Method ensures Type I and Type II error control and accurately identifies watermarked sub-strings.
Paper tackles source attribution for LLM-generated texts.
problem Identify the data provider of synthetic texts generated by LLMs.
method Watermarking to embed information about data providers in synthetic texts.
result Proposes and evaluates a source attribution framework that achieves effective source attribution.
PPO optimizes LLM-generated alpha weights for better trading performance.
problem Adapting LLM-generated alphas for varying market conditions.
method Proximal Policy Optimization (PPO) for dynamic alpha weight adjustment.
result PPO-optimized strategy achieves higher Sharpe ratios and smaller drawdowns.
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.
Improves feature selection in high-dimensional data using LLM-generated weights.
problem Inaccurate LLM-generated weights degrade feature selection performance.
method Integrates LLM-generated weights into prior inclusion probabilities using LLM Sparsity Prior (LSP).
result Improves prediction accuracy and identifies clinically relevant features.
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.
Unified AI detection framework for various artifacts.
problem Effective oversight and regulation of AI deployment.
method Unified detection framework based on Mahalanobis distance scores (MDS).
result Efficient and robust estimation of covariance matrix for positive samples.
LLM generates coherent macroeconomic stress scenarios for portfolio risk assessment.
problem Macro-financial stress testing and portfolio risk assessment using traditional methods.
method Hybrid prompt-RAG pipeline combining structured prompting and retrieval of country fundamentals and news.
result LLM-generated scenarios yield stable tail-risk amplification with limited sensitivity to retrieval choices.
Study uses LLMs to improve financial forecasting by integrating textual and numerical data.
problem Challenges in fusing multimodal information and measuring qualitative outputs from LLMs.
method Created context sets by segmenting daily securities reports into key factors and combining them with numerical data. Used dynamic updates and crafted prompts to assign scores to qualitative insights.
result LLMs outperform time-series models in market forecasting, though challenges remain.
Regurgitative training with synthetic data harms LLM performance.
problem The impact of training LLMs with synthetic data generated by other LLMs.
method Fine-tuning GPT-3.5 with synthetic and real data in a machine translation task.
result Regurgitative training significantly reduces LLM performance.
This paper combines LLMs with RL for better trading strategies.
problem Myopic behavior and opaque policies in RL for trading.
method LLMs generate strategic trading advice to guide RL agents.
result LLM-guided RL agents outperform unguided RL in return and risk metrics.
The paper applies communication theory to improve language model reranking.
problem Ensuring safety and accuracy in language model outputs.
method Drawing parallels between communication theory and language model reranking, the authors propose a protocol to improve reliability.
result The proposed protocol can achieve asymptotically error-free performance in noisy communication scenarios.
LLMs generate answers under incomplete context, and their uncertainty should scale with missing information.
problem Evaluating the quality of LLM answers under incomplete context.
method A controlled framework with varying context availability, and two uncertainty measures (sampling-based confidence and response entropy) evaluated on SQuAD.
result Response entropy increases with context removal and explains more variance in accuracy than confidence, suggesting it is a more responsive uncertainty measure.
PandaAI: A practical agent for neuro-symbolic data analysis and decision-making in finance
problem Sequential decision-making in finance
method Leveraging LLMs for market regime modeling and constrained alpha generation
result PandaAI achieves higher Rank IC and lower maximum drawdown
Framework identifies causal factors of climate change using correlations and machine learning.
problem Understanding socioeconomic factors influencing carbon emissions and climate change.
method Three-step framework: correlation analysis, causal discovery, LLM interpretations.
result Adaptable solutions for data-driven policy-making and strategic decision-making.
Computer science scans LLMs to understand and manipulate their economic forecasts.
problem Understanding and controlling the reasoning of large language models in economics.
method Brain scanning techniques applied to LLMs to identify and manipulate underlying concepts.
result LLMs can be steered to generate forecasts with specific biases, allowing for correction or simulation.
Develops a power-calibrated framework for LLM watermarking, optimizing tradeoffs between detectability and distortion.
problem The trade-off between detectability and semantic distortion in logit-based watermarking.
method Power-calibrated statistical framework for watermark hyperparameters, establishing explicit relationships.
result Derives practical parameter selection procedures achieving optimal tradeoffs under constraints.
LLMs struggle with financial reasoning but can outperform the market with human oversight.
problem Financial reasoning failures in LLM-generated stock market predictions.
method Evaluated four LLMs using three prompting strategies and compared to human oversight.
result LLMs require human oversight to fully realize their potential in financial markets.
LLMs are compared to Markov chains for natural language processing.
problem Theoretical analysis of LLMs' generalization capabilities.
method Equivalence between LLMs and Markov chains, studying multi-step inference.
result Derives generalization bounds for LLMs, capturing their behavior in practice.
This work introduces RISE to explain LLMs more reliably by distinguishing essential context.
problem Identifying which context elements influence LLM outputs reliably.
method RISE (Redundancy-Insensitive Scoring of Explanation) method.
result RISE provides more robust explanations than traditional methods.
Scene text magnifier aims to magnify text in natural scene images without recognition. It could help the special groups, who have myopia or dyslexia to better understand the scene. In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, char…
The paper classifies actions of a specific group on certain manifolds.
problem Classifying analytic actions of a specific semi-orthogonal group on manifolds.
method Adapting Uchida's construction, the paper explicitly constructs actions on specific manifolds and demonstrates that any action is covered by these.
result Any analytic action of the semi-orthogonal group on a closed, connected manifold is covered by the constructed actions.
The paper solves the Nielsen realization problem for high degree del Pezzo surfaces.
problem Which finite subgroups of the mapping class group of a del Pezzo surface lift to the diffeomorphism group?
method Classification and partial answers for d≥7, equivariant connected sum for d=6. result Complete classification for d≥7, partial answer for d=6. New bounds show large language models can generalize beyond training data.
problem Generalization of large language models beyond training data.
method Compression bound derivation using prediction smoothing and SubLoRA.
result Large language models can discover generalizable regularities.
We establish a gluing construction for Higgs bundles over a connected sum of Riemann surfaces in terms of solutions to the Sp(4,R)-Hitchin equations using the linearization of a relevant elliptic operator. The construction can be used to provide model Higgs bundles in all the 2g−3 exce…
A new text representation model combines CNN and VAE for better semantic extraction.
problem Difficult to effectively extract semantic features and distinguish polysemy in text data.
method Integrates CNN for feature extraction and VAE for consistent Gaussian distribution.
result The model outperforms traditional classification algorithms in text classification tasks.
We propose two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general stochastic nonconvex optimization. At the core of the proposed algorithms is One-epoch-SNVRG+ using stochastic nested variance reduction (Zhou et al., 2018a), which outperforms the s…
New families of Lie groups with special foliations discovered.
problem Characterizing left-invariant foliations on semi-Riemannian Lie groups.
method Classifying foliations generated by specific subgroups.
result Constructing new families of Lie groups with conformal minimal foliations.
Improved text summarization using belief propagation on weighted bipartite graphs.
problem Text summarization from a graph theory perspective.
method Generalized belief propagation algorithm for weighted bipartite graphs.
result Our algorithm outperforms greedy methods in text summarization tasks.
New TC variant dTC better fits motion planning for some systems.
problem Improving motion planning for autonomous systems.
method Defined and computed new homotopy invariant dTC.
result dTC and dcat provide better motion planning solutions.
Let Man∗ denote the category of closed, connected, oriented and based 3-manifolds, with basepoint preserving diffeomorphisms between them. Juhász, Thurston and Zemke showed that the Heegaard Floer invariants are natural with respect to diffeomorphisms, in the sense that there are functors $HF^{\circ}: \te…
Paper generates diverse, readable adversarial texts from scratch.
problem Text classification models are easily fooled by adversarial examples.
method Trained a conditional variational autoencoder (VAE) with adversarial loss and utilized GANs to generate consistent adversarial texts.
result Successfully generates adversarial texts with higher success rate and acceptable quality.
SCROLLS benchmarks long text NLP tasks, improving existing models.
problem Short NLP benchmarks ignore long texts; SCROLLS addresses this.
method Handpicked long-text datasets for summarization, QA, and inference tasks.
result Improvement potential on SCROLLS tasks, as indicated by initial baselines.
We detect lookahead bias in LLM forecasts using a novel statistical method.
problem Detecting lookahead bias in LLM-generated economic forecasts.
method Developed a statistical procedure using date-only recall queries and estimated Lookahead Propensity (LAP).
result LLM forecasts are contaminated with lookahead bias, as indicated by a positive interaction between LAP and the forecast in accuracy regressions.
New method detects text changes under dependencies, outperforming baselines.
problem Detecting structural changes in m-dependent text data. method Kernel change-point detection under m-dependence. result Consistent and weakly consistent detection of change points in m-dependent text. Contextual bandits study how reward variance affects regret bounds.
problem Investigating how small reward variance impacts regret bounds in contextual bandits.
method Analyzing two types of adversaries and function approximation complexities.
result Regret bounds are influenced by the eluder dimension and reward variance.