Related papers: LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Se…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks. The goal is to balance general language proficiency with domain-specific skills. The…

In recent years, large language models (LLMs) have achieved remarkable success in natural language processing (NLP). LLMs require an extreme amount of parameters to attain high performance. As models grow into the trillion-parameter range,…

Large Language Models (LLMs) have demonstrated strong performance across general NLP tasks, but their utility in automating numerical experiments of complex physical system -- a critical and labor-intensive component -- remains…

Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and…

Large Language Models (LLMs) based on the pre-trained fine-tuning paradigm have become pivotal in solving natural language processing tasks, consistently achieving state-of-the-art performance. Nevertheless, the theoretical understanding of…

Recently, Large Language Models (LLMs) have garnered increasing attention in the field of natural language processing, revolutionizing numerous downstream tasks with powerful reasoning and generation abilities. For example, In-Context…

This study investigates the adoption of open-access, locally deployable causal large language models (LLMs) for travel mode choice prediction and introduces LiTransMC, the first fine-tuned causal LLM developed for this task. We…

Large language models (LLMs) have achieved remarkable success across widespread tasks, yet their application in low-resource domains remains a significant challenge due to data scarcity and the high risk of overfitting. While in-domain data…

Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges,…

Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behaviors. Large language models (LLMs), with their pretraining on vast corpora containing rich…

Large language models (LLMs) have achieved strong performance across a wide range of natural language processing tasks. However, deploying LLMs at scale for domain specific applications, such as job-person fit and explanation in job seeking…

Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains, thereby prompting researchers to explore their potential for use in recommendation systems. Initial attempts have leveraged the exceptional…

Evaluating Large Language Models (LLMs) with respect to real-world code complexity is essential. Otherwise, there is a risk of overestimating LLMs' programming abilities based on simplistic benchmarks, only to be disappointed when using…

Large Language Models (LLMs) are distinguished by their architecture, which dictates their parameter size and performance capabilities. Social scientists have increasingly adopted LLMs for text classification tasks, which are difficult to…

The pervasive deployment of Large Language Models-LLMs in various sectors often neglects the nuanced requirements of individuals and small organizations, who benefit more from models precisely tailored to their specific business contexts…

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

Evaluating Large Language Models (LLMs) is one of the most critical aspects of building a performant compound AI system. Since the output from LLMs propagate to downstream steps, identifying LLM errors is crucial to system performance. A…

As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English speakers. Current methods to enhance multilingual…

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…