AI
Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks
Researchers have developed a framework called Bactrainus to improve large language models' ability t...
AI
Gradient Heterogeneity Complements Hessian Heterogeneity in Transformer Optimization
Researchers have analyzed how gradient heterogeneity affects the optimization of Transformer models....
AI
MCTS-KBQA: Monte Carlo Tree Search with Information Gain Rewards for Knowledge Base Question Answering
Researchers propose a new method for improving large language model-based reasoning in knowledge bas...
AI
Beyond BFI: The CSI for Enhanced Reliability and Validity in Evaluating LLM Personality Traits
A new evaluation tool called the Core Sentiment Inventory (CSI) is proposed to assess the personalit...
AI
LZ Penalty: An information-theoretic repetition penalty for autoregressive language models
Researchers have introduced the LZ penalty, a new method for reducing repetition...
AI
TabularQGAN: A quantum generative model for tabular data synthesis
Researchers have developed a new quantum generative model called TabularQGAN for...
AI
Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios
Researchers have developed a new method to improve the processing of hyperspectr...
AI
Hidden Prompts in Manuscripts Exploit AI-Assisted Peer Review
Researchers have discovered that some authors are hiding instructions in their m...