To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples

A recent study investigates bias in generative AI text annotations, replicating manual annotations from Boukes (2024) using various Generative Large Language Models (GLLMs) including Llama3.1, Llama3.3, GPT4o, and Qwen2.5. The findings indicate that while GLLMs achieve adequate F1 scores, they exhibit systematic bias, aligning more closely with each other than with manual annotations, which leads to different downstream results.

A comprehensive survey on deep transfer learning for image classification has been published, highlighting the effectiveness of deep neural networks like CNNs and transformers in scenarios where large labeled datasets are unavailable. The survey emphasizes the importance of transfer learning in enhancing performance under such constraints.

A systematic study has revealed that chain-of-thought (CoT) prompting, which is often used to enhance reasoning in large language models (LLMs), fails to improve performance in clinical text understanding. The research assessed 95 advanced LLMs across 87 real-world clinical tasks, finding that 86.3% of models experienced performance degradation in CoT settings, particularly with electronic health records that are lengthy and fragmented.

The introduction of UniQL, a unified post-training quantization and low-rank compression framework, addresses the challenges of deploying large language models (LLMs) on mobile platforms, which often face limitations in memory and computational resources. This framework allows for on-device configurable pruning rates, enhancing the adaptability of edge LLMs.

A recent survey on optimal and diffusion transports in machine learning highlights the significance of time-evolving probability distributions in various applications, including sampling, neural network optimization, and token distribution analysis in large language models. The study emphasizes the transition from Eulerian to Lagrangian representations, which introduces both challenges and opportunities for crafting effective density evolutions.