Related papers: Generative Adapter: Contextualizing Language Model…

Retrieval-Augmented Generation (RAG) has emerged as a prominent method for incorporating domain knowledge into Large Language Models (LLMs). While RAG enhances response relevance by incorporating retrieved domain knowledge in the context,…

Accurately simulating the decisions of a specific individual remains challenging for large language models (LLMs), partly because persona information is often provided as static descriptions that miss the values, experiences, and contextual…

Large Language Models (LLMs), being generic task solvers, are versatile. However, despite the vast amount of data they are trained on, there are speculations about their adaptation capabilities to a new domain. Additionally, the simple…

Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where…

Adapting state-of-the-art Large Language Models (LLMs) like GPT-4 and Gemini for specific tasks is challenging. Due to the opacity in their parameters, embeddings, and even output probabilities, existing fine-tuning adaptation methods are…

This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have…

Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context…

Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity arising from the diversity of valid responses. These…

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…

Multilingual machine translation suffers from negative interference across languages. A common solution is to relax parameter sharing with language-specific modules like adapters. However, adapters of related languages are unable to…

Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its…

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…

Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called…

Generative large language models (LLMs) are a promising alternative to pre-trained language models for entity matching due to their high zero-shot performance and ability to generalize to unseen entities. Existing research on using LLMs for…

Parameter efficient adaptation methods have become a key mechanism to train large pre-trained models for downstream tasks. However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for…

Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the…

With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have…

Efficient finetuning of pretrained language transformers is becoming increasingly prevalent for solving natural language processing tasks. While effective, it can still require a large number of tunable parameters. This can be a drawback…

This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…