Related papers: Orca: Progressive Learning from Complex Explanatio…

Models like GPT-4o enable real-time interaction with large language models (LLMs) through speech, significantly enhancing user experience compared to traditional text-based interaction. However, there is still a lack of exploration on how…

Large language models (LLMs), such as GPT-4, PaLM, and LLaMa, have been shown to achieve remarkable performance across a variety of natural language tasks. Recent advancements in instruction tuning bring LLMs with ability in following…

Large Multimodal Models (LMMs) have demonstrated exceptional performance across a wide range of domains. This paper explores their potential in pronunciation assessment tasks, with a particular focus on evaluating the capabilities of the…

While task-specific demonstrations show early success in applying large language models (LLMs) to automate some astronomical research tasks, they only provide incomplete views of all necessary capabilities in solving astronomy problems,…

Large language models (LLMs) have shown great potential for the automatic generation of feedback in a wide range of computing contexts. However, concerns have been voiced around the privacy and ethical implications of sending student work…

Chain-of-Thought (CoT) reasoning has significantly advanced state-of-the-art AI capabilities. However, recent studies have shown that CoT reasoning is not always faithful when models face an explicit bias in their prompts, i.e., the CoT can…

Large Language Models (LLMs) have been applied to Math Word Problems (MWPs) with transformative impacts, revolutionizing how these complex problems are approached and solved in various domains including educational settings. However, the…

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in natural language processing. In this work, we identify a…

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of natural language tasks; however, their large size makes their inference slow and computationally expensive. Focusing on this problem, we propose to…

Prompting techniques have significantly enhanced the capabilities of Large Language Models (LLMs) across various complex tasks, including reasoning, planning, and solving math word problems. However, most research has predominantly focused…

Proof assistants like Lean have revolutionized mathematical proof verification, ensuring high accuracy and reliability. Although large language models (LLMs) show promise in mathematical reasoning, their advancement in formal theorem…

Large multimodal models extend the impressive capabilities of large language models by integrating multimodal understanding abilities. However, it is not clear how they can emulate the general intelligence and reasoning ability of humans.…

When primed with only a handful of training samples, very large, pretrained language models such as GPT-3 have shown competitive results when compared to fully-supervised, fine-tuned, large, pretrained language models. We demonstrate that…

The use of large language models in digital forensics has been widely explored. Beyond identifying potential applications, research has also focused on optimizing model performance for forensic tasks through fine-tuning. However, limited…

Recent impressive results from large reasoning models have been interpreted as a triumph of Chain of Thought (CoT), and especially of the process of training on CoTs sampled from base LLMs in order to help find new reasoning patterns. While…

Recent progress in reasoning-oriented Large Language Models (LLMs) has been driven by introducing Chain-of-Thought (CoT) traces, where models generate intermediate reasoning traces before producing an answer. These traces, as in DeepSeek…

Large Language Models (LLMs) excel at extracting common patterns from large-scale corpora, yet they struggle with rare, low-resource, or previously unseen scenarios-such as niche hardware deployment issues or irregular IoT device…

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Large Foundational Language Models are capable of performing many tasks at a high level but are difficult to deploy in many applications because of their size and proprietary ownership. Many will be motivated to distill specific…

In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation. We discover that LLM's performance exceeds humans and surpasses the…