6 papers
IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation
Johannes Schmitt, Gergely Bérczi, Jasper Dekoninck +57
As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of…
How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns
Haoyue Bai, Yiyou Sun, Wenjie Hu +5
Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tunin…
Estimating the Self-Consistency of LLMs
Robert Nowak
Systems often repeat the same prompt to large language models (LLMs) and aggregate responses to improve reliability. This short note analyzes an estimator of the self-consistency o…
Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Yang Guo, Yutian Tao, Yifei Ming +2
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostl…
BowelRCNN: Region-based Convolutional Neural Network System for Bowel Sound Auscultation
Igor Matynia, Robert Nowak
Sound events representing intestinal activity detection is a diagnostic tool with potential to identify gastrointestinal conditions. This article introduces BowelRCNN, a novel bowe…
Quality evaluation of Tabby coding assistant using real source code snippets
Marta Borek, Robert Nowak
Large language models have become a popular tool in software development, providing coding assistance. The proper measurement of the accuracy and reliability of the code produced b…