Related papers: Fine-Tuning Enhances Existing Mechanisms: A Case S…
Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge. It is commonly believed that fine-tuning can surpass ICL given sufficient training samples as it allows the…
Large language models (LLMs) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…
Code generation and understanding are critical capabilities for large language models (LLMs). Thus, most LLMs are pretrained and fine-tuned on code data. However, these datasets typically treat code as static strings and rarely exploit the…
To improve the performance on a target task, researchers have fine-tuned language models with an intermediate task before the target task of interest. However, previous works have focused on the pre-trained language models and downstream…
Pre-trained language models can be fine-tuned to solve diverse NLP tasks, including in few-shot settings. Thus fine-tuning allows the model to quickly pick up task-specific ``skills,'' but there has been limited study of where these…
Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…
Understanding the internal mechanisms of large language models (LLMs) remains a challenging and complex endeavor. Even fundamental questions, such as how fine-tuning affects model behavior, often require extensive empirical evaluation. In…
Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited. However, different PELT methods…
Learner-item cognitive modeling plays a central role in the web-based online intelligent education system by enabling cognitive diagnosis (CD) across diverse online educational scenarios. Although ID embedding remains the mainstream…
Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large…
Previous research has shown that fine-tuning language models on general tasks enhance their underlying mechanisms. However, the impact of fine-tuning on poisoned data and the resulting changes in these mechanisms are poorly understood. This…
Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model…
Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and reason outside of…
Large Language Models (LLMs) fine-tuned for specific domains exhibit strong performance; however, the underlying mechanisms by which this fine-tuning reshapes their parametric space are not well understood. Prior works primarily focus on…
The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…
Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of…
Language Models are the underpin of all modern Natural Language Processing (NLP) tasks. The introduction of the Transformers architecture has contributed significantly into making Language Modeling very effective across many NLP task,…
Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…
Many recent works on Entity Resolution (ER) leverage Deep Learning techniques involving language models to improve effectiveness. This is applied to both main steps of ER, i.e., blocking and matching. Several pre-trained embeddings have…
Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target…