相关论文: Leveraging Data Augmentation and Siamese Learning …

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…

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…

Purpose- The significance of business processes has fostered a close collaboration between academia and industry. Moreover, the business landscape has witnessed continuous transformation, closely intertwined with technological advancements.…

Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task. LLMs have been successfully used to help find and improve prompt candidates for single-step tasks. However, realistic tasks for agents are…

We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribute equally to the…

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific…

The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strategies, such as memory-based retrieval or preference…

Spatio-temporal forecasting is pivotal in numerous real-world applications, including transportation planning, energy management, and climate monitoring. In this work, we aim to harness the reasoning and generalization abilities of…

Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Process supervision, i.e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute. Existing approaches, represented by process reward models (PRMs),…

State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g. LSTMs) proved extremely successful in modeling complex time series…

Predictive analysis in business process monitoring aims at forecasting the future information of a running business process. The prediction is typically made based on the model extracted from historical process execution logs (event logs).…

Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits…

Numerous process discovery techniques exist for generating process models that describe recorded executions of business processes. The models are meant to generalize executions into human-understandable modeling patterns, notably…

The proliferation of capable and efficient machine learning (ML) models marks one of the strongest methodological shifts in signal processing (SP) in its nearly 100-year history. ML models support the development of SP systems that…

In recent years, the rise of Large Language Models (LLMs) has spurred a growing demand for plug-and-play AI systems. Among the various AI techniques, prompt engineering stands out as particularly significant. However, users often face…

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

This paper proposes a novel sparse principal component analysis algorithm with self-learning ability for successive modes, where synaptic intelligence is employed to measure the importance of variables and a regularization term is added to…