相关论文: Weight Patching: Toward Source-Level Mechanistic L…

Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data inputs, especially for MLLMs that have been fine-tuned for…

Local-nonlocal coupling approaches combine the computational efficiency of local models and the accuracy of nonlocal models. However, the coupling process is challenging, requiring expertise to identify the interface between local and…

Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop highly structured representations. When such…

Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model's reasoning on an objective task. Using activation patching, we take a first step…

Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…

Understanding the internal mechanisms of large language models (LLMs) is integral to enhancing their reliability, interpretability, and inference processes. We present Constituent-Aware Pooling (CAP), a methodology designed to analyse how…

The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too…

Machine Learning models from other fields, like Computational Linguistics, have been transplanted to Software Engineering tasks, often quite successfully. Yet a transplanted model's initial success at a given task does not necessarily mean…

Current Large Language Models (LLMs) excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. Fine-tuning large models for every niche application is often infeasible due to…

Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to…

Large pre-trained models have enabled significant advances in machine learning and served as foundation components. Model fusion methods, such as task arithmetic, have been proven to be powerful and scalable to incorporate fine-tuned…

Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

LLM-based agents are becoming central to software engineering tasks, yet evaluating them remains fragmented and largely model-centric. Existing studies overlook how architectural components, such as planners, memory, and tool routers, shape…

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating…

Emergent Large Language Models (LLMs) use their extraordinary performance and powerful deduction capacity to discern from traditional language models. However, the expenses of computational resources and storage for these LLMs are stunning,…

Large language models (LLMs) deliver impressive results for a variety of tasks, but state-of-the-art systems require fast GPUs with large amounts of memory. To reduce both the memory and latency of these systems, practitioners quantize…

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignment: residual connections tie activations to the current…

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Vision Language Models (VLMs) play a crucial role in robotic manipulation by enabling robots to understand and interpret the visual properties of objects and their surroundings, allowing them to perform manipulation based on this multimodal…