Related papers: Improving Large Language Model Planning with Actio…

In recent research advancements within the community, large language models (LLMs) have sparked great interest in creating autonomous agents. However, current prompt-based agents often heavily rely on large-scale LLMs. Meanwhile, although…

LLM alignment ensures that large language models behave safely and effectively by aligning their outputs with human values, goals, and intentions. Aligning LLMs employ huge amounts of data, computation, and time. Moreover, curating data…

Multi-modal Large Language Model (MLLM) refers to a model expanded from a Large Language Model (LLM) that possesses the capability to handle and infer multi-modal data. Current MLLMs typically begin by using LLMs to decompose tasks into…

Planning in complex environments requires an agent to efficiently query a world model to find a feasible sequence of actions from start to goal. Recent work has shown that Large Language Models (LLMs), with their rich prior knowledge and…

This study focuses on improving the performance of lightweight Large Language Models (LLMs) in mathematical reasoning tasks. We introduce a novel method for measuring mathematical logic similarity and design an automatic screening mechanism…

In-context learning (ICL) and supervised fine-tuning (SFT) are two common strategies for improving the performance of modern large language models (LLMs) on specific tasks. Despite their different natures, these strategies often lead to…

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

As world knowledge advances and new task schemas emerge, Continual Learning (CL) becomes essential for keeping Large Language Models (LLMs) current and addressing their shortcomings. This process typically involves continual instruction…

Large language models (LLMs), such as LLaMA, Alpaca, Vicuna, GPT-3.5 and GPT-4, have advanced the performance of AI systems on various natural language processing tasks to human-like levels. However, their generalisation and robustness when…

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a…

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. While many real-world applications still require fine-tuning to reach satisfactory levels of…

The inherent probabilistic nature of Large Language Models (LLMs) introduces an element of unpredictability, raising concerns about potential discrepancies in their output. This paper introduces an innovative approach aims to generate…

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…

Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveraging a few demonstrations pertaining to a new downstream task as conditions. However, this particular learning paradigm suffers from high…

Large language models (LLMs) have shown remarkable in-context learning (ICL) capabilities, yet their potential for sequential decision-making remains underexplored. In this paper, we study the ICL capabilities of LLMs in sequential…

Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields. In this…

Aligning Large Language Models (LLMs) with human preferences through finetuning is resource-intensive, motivating lightweight alternatives at test time. We address test-time alignment through the lens of sequential decision making, a…

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…