Dataset of human-written problem statements and solutions for program synthesis.
problem Creating programs from natural language problem descriptions.
method Crowdsourced problem statements and solutions from programming competitions.
result Best model achieved 8.8% accuracy, indicating high complexity.
Study uses AI to refine loan assessments, improving credit default predictions.
problem Improving credit default prediction accuracy using AI-refined text.
method Comparative analysis of human-written and AI-refined loan assessments using deep learning techniques.
result AI-refined texts significantly enhance credit default predictions, especially when combined with structured data.
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.
Improved text generation with discourse-aware soft prompts.
problem Efficient fine-tuning methods don't generalize across all generation tasks.
method Hierarchical blocking and attention sparsity on prefix parameters.
result Structured design of prefix parameters yields more coherent generations.
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.
Study evaluates human vs. machine review generation, finds human assessments correlate better with lexical overlaps.
problem Evaluating natural language generation models for online reviews is challenging and inconsistent.
method Compared human evaluators with various automated evaluation methods, including discriminative and word overlap metrics.
result Human evaluators do not correlate well with discriminative evaluators, but correlate better with lexical overlaps.
AI generates theorems and proofs for training theorem provers.
problem Limited human-written theorems and proofs for supervised learning.
method Proposes a neural generator to automatically synthesize theorems and proofs.
result Synthetic data improves automated theorem proving in Metamath.
A new neural network model for sentiment analysis.
problem Accurate and transferable sentiment analysis models.
method A computationally-efficient feedforward neural network.
result Highly accurate models with low losses.
Unified framework for online LLM watermark detection using e-processes.
problem Detecting AI-generated text from human-written content in online settings.
method Unified framework based on e-processes for anytime-valid hypothesis testing on independence.
result Proposed methods achieve competitive performance in watermark detection.
Machine learning automates proof generation in Coq proof assistant.
problem Automating proof construction in proof assistants.
method Developed ASTactic, a deep learning model generating tactics as ASTs.
result ASTactic can generate effective tactics and prove new theorems.
Computer generated academic papers have been used to expose a lack of thorough human review at several computer science conferences. We assess the problem of classifying such documents. After identifying and evaluating several quantifiable features of academic papers, we apply methods from machine learning to build a b…
Paper develops an efficient online watermark detection for AI-generated text.
problem Detecting AI-generated text from human-written content efficiently.
method Rao-Blackwellized e-processes for anytime-valid inference in streaming generation.
result The method enables recursive token-level evidence updates without storing full history.
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.
Variance-Calibrated Modulation (VCM) addresses the likelihood trap in LLMs by reshaping the probability distribution before truncation.
problem LLMs fall into the likelihood trap, leading to repetitive degeneration and vocabulary dullness.
method VCM reshapes the probability distribution before truncation through Contextual Searchlight and Adaptive Self-Debiasing.
result VCM mitigates the likelihood trap across open-ended generation, factual QA, and mathematical reasoning.
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.
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.
Study on estimating Gumbel--Max watermark proportions in edited documents.
problem Estimating the proportion of a document generated from a watermarked LLM.
method Comparison of full observation and pivotal reduction observation regimes; development of estimators and information-theoretic lower bounds.
result Full observation yields a substantially smaller sample complexity compared to pivotal reduction.
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.