Related papers: AIDE: Attribute-Guided MultI-Hop Data Expansion fo…

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

For the purpose of maximizing the spread of influence caused by a certain small number k of nodes in a social network, we are asked to find a k-subset of nodes (i.e., a seed set) with the best capacity to influence the nodes not in it. This…

Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…

While Monte Carlo Tree Search (MCTS) shows promise in Large Language Model (LLM) based Automatic Heuristic Design (AHD), it suffers from a critical over-exploitation tendency under the limited computational budgets required for heuristic…

Fine-tuning all parameters of Large Language Models (LLMs) is computationally expensive. Parameter-Efficient Fine-Tuning (PEFT) methods address this by selectively fine-tuning specific parameters. Most of the parameter efficient fine-tuning…

The hypothesis that pretrained large language models (LLMs) necessitate only minimal supervision during the fine-tuning (SFT) stage (Zhou et al., 2024) has been substantiated by recent advancements in data curation and selection research.…

Information Extraction (IE) systems are traditionally domain-specific, requiring costly adaptation that involves expert schema design, data annotation, and model training. While Large Language Models have shown promise in zero-shot IE,…

Training LLMs to invoke tools and leverage retrieved information necessitates high-quality, diverse data. However, existing pipelines for synthetic data generation often rely on tens of thousands of real API calls to enhance generalization,…

Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing…

While differentially private (DP) fine-tuning of large language models (LLMs) is a powerful tool, it is often computationally prohibitive or infeasible when state-of-the-art models are only accessible via proprietary APIs. In such settings,…

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various…

Person re-identification (Re-ID) is a crucial task in computer vision, aiming to recognize individuals across non-overlapping camera views. While recent advanced vision-language models (VLMs) excel in logical reasoning and multi-task…

Deep neural networks require a large amount of labeled training data during supervised learning. However, collecting and labeling so much data might be infeasible in many cases. In this paper, we introduce a source-target selective joint…

Autonomous agents operating on the graphical user interfaces (GUIs) of various applications hold immense practical value. Unlike the large language model (LLM)-based methods which rely on structured texts and customized backends, the…

Although many AI applications of interest require specialized multi-modal models, relevant data to train such models is inherently scarce or inaccessible. Filling these gaps with human annotators is prohibitively expensive, error-prone, and…

Constructing accurate knowledge graphs from long texts and low-resource languages is challenging, as large language models (LLMs) experience degraded performance with longer input chunks. This problem is amplified in low-resource settings…

The ability for a human to understand an Artificial Intelligence (AI) model's decision-making process is critical in enabling stakeholders to visualize model behavior, perform model debugging, promote trust in AI models, and assist in…

In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inherently vulnerable to knowledge overshadowing - a phenomenon…

Approximate probabilistic inference algorithms are central to many fields. Examples include sequential Monte Carlo inference in robotics, variational inference in machine learning, and Markov chain Monte Carlo inference in statistics. A key…

Multimodal large language models (MLLMs) demonstrate exceptional capabilities in semantic understanding and visual reasoning, yet they still face challenges in precise object localization and resource-constrained edge-cloud deployment. To…