Large Language Models (LLMs) have become increasingly important in AI and data processing tasks, but their superior size leads to substantial memory requirements and bandwidth consumption. Standard procedures such as Post-Training Quantization (PTQ) and Quantized Parameter-Efficient Fine-Tuning (Q-PEFT) can often compromise accuracy and performance, and are impractical for larger networks. To combat this, researchers have…
Language models (LMs), used in applications such as autocomplete and language translation, are trained on a vast amount of text data. Yet, these models also face significant challenges in relation to privacy and copyright concerns. In some cases, the inadvertent inclusion of private and copyrighted content in training datasets can lead to legal and ethical…
Researchers at the University of Texas (UT) in Austin have introduced a new benchmark designed to evaluate the effectiveness of artificial intelligence in solving complex mathematical problems. PUTNAMBENCH is aimed at solving a key issue facing the sector as current benchmarks are not sufficiently rigorous and mainly focus on high-school level mathematics.
Automating mathematical reasoning…
DeepSeek has announced the launch of its advanced open-source AI model, DeepSeek-V2-Chat-0628, on Hugging Face. The update represents a significant advancement in AI text generation and chatbot technology. This new version secures the overall ranking of #11 according to the LMSYS Chatbot Arena Leaderboard, outperforming all other existing open-source models. It is an upgrade on…
Large Language Models (LLMs) are vital for tasks in natural language processing but they encounter issues when it comes to deployment. This is due to their substantial computational and memory requirements during inference. Current research studies are focused on boosting LLM efficiency by applying methods such as quantization, pruning, distillation, and improved decoding. One of…
Generative artificial intelligence (AI) technologies, like Large Language Models (LLMs), are showing promise in areas like programming processes, customer service productivity, and collaborative storytelling. However, their impact on human creativity, a cornerstone of our behavior, is still somewhat unknown. To investigate this, a research team from the University College London and the University of Exeter…
Large language models (LLMs) are being extensively used in multiple applications. However, they have a significant limitation: they struggle to process long-context tasks due to the constraints of transformer-based architectures. Researchers have explored various approaches to boost LLMs' capabilities in processing extended contexts, including improving softmax attention, reducing computational costs and refining positional encodings. Techniques…
Researchers from the Shanghai AI Laboratory and Tsinghua University have developed NeedleBench, a novel framework to evaluate the retrieval and reasoning capabilities of large language models (LLMs) in exceedingly long contexts (up to 1 million tokens). The tool is critical for real-world applications such as legal document analysis, academic research, and business intelligence, which rely…
The use of offline web and AI apps often encounters several hurdles. Users typically face multiple steps to get an app up and running, and those who aren't technically proficient may find the process confusing and lengthy. Furthermore, the management and customization of these apps often necessitate manual file editing, exacerbating the problem.
However, the introduction…
The surge of low-quality data online has led to potentially harmful knowledge instilled in Large Language Models (LLMs). This problem elevates risks when LLMs are deployed in chatbots that might expose users to harmful advice or aggressive interactions. Existing toxicity evaluation datasets focus mainly on English, limiting their capability to detect multilingual toxicity which compromises…
The task of translating natural language queries (text-to-SQL) into SQL has been historically challenging due to the complexity of understanding user questions, database schemas, and SQL production. Recent innovations have seen the integration of Pre-trained Language Models (PLMs) into text-to-SQL systems, which have displayed much promise. However, they can generate incorrect SQL due to growing…
Despite their advancement in many language processing tasks, large language models (LLMs) still have significant issues when it comes to complex mathematical reasoning. Current methodologies have difficulty decomposing tasks into manageable sections and often lack useful feedback from tools that might supplement a comprehensive analysis. While existing methods perform well on simpler problems, they generally…