Related papers: Fine-Tuning Small Language Models (SLMs) for Auton…

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…

Real-world path planning tasks typically involve multiple constraints beyond simple route optimization, such as the number of routes, maximum route length, depot locations, and task-specific requirements. Traditional approaches rely on…

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM)…

Large language models (LLMs) have shown promise for event log analysis, but their high computational requirements, reliance on cloud infrastructure, and security concerns limit practical deployment. In addition, most existing approaches…

Running language models in the browser presents a unique opportunity to build efficient, private, and portable AI applications, but requires contending with constrained memory availability and heterogeneous hardware targets. To realize this…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and code has made them ubiquitous in many fields, while their…

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…

Translation-tailored Large language models (LLMs) exhibit remarkable translation capabilities, even competing with supervised-trained commercial translation systems. However, off-target translation remains an unsolved problem, especially…

Integrating large language models (LLMs) with knowledge graphs derived from domain-specific data represents an important advancement towards more powerful and factual reasoning. As these models grow more capable, it is crucial to enable…

Visual geo-localization demands in-depth knowledge and advanced reasoning skills to associate images with precise real-world geographic locations. Existing image database retrieval methods are limited by the impracticality of storing…

Fine-tuning a large language model (LLM) using the local data of edge users can enable personalized services and applications. For privacy protection, the prevalent solution adopts distributed learning for fine-tuning and integrates…

Text-to-SQL prompt strategies based on Large Language Models (LLMs) achieve remarkable performance on well-known benchmarks. However, when applied to real-world databases, their performance is significantly less than for these benchmarks,…

Automated Short Answer Scoring (ASAS) is a critical component in educational assessment. While traditional ASAS systems relied on rule-based algorithms or complex deep learning methods, recent advancements in Generative Language Models…

Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…

The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems…

Recent advances in large language models (LLMs) have fueled growing interest in automating geospatial analysis and GIS workflows, yet their actual capabilities remain uncertain. In this work, we call for rigorous evaluation of LLMs on…

Artificially intelligent (AI) co-scientists must be able to sift through research literature cost-efficiently while applying nuanced scientific reasoning. We evaluate Small Language Models (SLMs, <= 8B parameters) for classifying medical…

The advent of large language models (LLMs) revolutionized natural language processing applications, and running LLMs on edge devices has become increasingly attractive for reasons including reduced latency, data localization, and…