AI
AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction
Researchers have developed AISA, a framework that uses large language models to improve highway cons...
AI
Which Source Wins? Task-Dependent Reliance in Vision-Language Models
Researchers studied how vision-language models (VLMs) handle conflicting information between images ...
AI
The Plot Thins: Uniformity and Linearity in Literary Summaries
Researchers have created a dataset that maps sentences from literary summaries to their original cha...
AI
Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal
Researchers have found that temporal leakage in financial news NLP can significantly affect model pe...
AI
Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention
Researchers have proposed Q-Interference, a quantum-inspired attention mechanism...
AI
What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?
Researchers analyzed how tokenization affects language modeling performance acro...
AI
ArguLens: An Open-Source System for Automated Essay Scoring and Label-Aware Feedback Generation
Researchers have developed ArguLens, an open-source system for automated essay s...
AI
An Investigation of Translationese in the Generations of Multilingual Large Language Models
Researchers investigated whether multilingual large language models (MLLMs) gene...