相关论文: Overtrained, Not Misaligned

Recent research has highlighted the importance of dataset size in scaling language models. However, large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its…

Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundational coding knowledge on large, general-purpose datasets…

This work introduces EE-Tuning, a lightweight and economical solution to training/tuning early-exit large language models (LLMs). In contrast to the common approach of full-parameter pre-training, EE-Tuning augments any pre-trained (and…

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…

Mixture-of-Experts (MoE) models have emerged as a dominant paradigm for efficient LLM scaling, yet adapting them to non-English downstream tasks remains challenging. Existing fine-tuning approaches treat MoE models as monolithic learners,…

Entity Matching (EM) involves identifying different data representations referring to the same entity from multiple data sources and is typically formulated as a binary classification problem. It is a challenging problem in data integration…

In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code…

The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an inherent limitation for long autoregressive outputs. Our…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…

Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. However, in certain specialized domains, such as healthcare or…

Iterative self-correction is increasingly deployed in agentic LLM systems, yet whether repeated refinement improves or degrades performance remains inconsistent across models. We recast self-correction as a closed-loop feedback-control…

Parameter-Efficient Tuning (PETuning) methods have been deemed by many as the new paradigm for using pretrained language models (PLMs). By tuning just a fraction amount of parameters comparing to full model finetuning, PETuning methods…

We investigate the convergence properties of the EM algorithm when applied to overspecified Gaussian mixture models -- that is, when the number of components in the fitted model exceeds that of the true underlying distribution. Focusing on…

Generalized Entity Matching (GEM), which aims at judging whether two records represented in different formats refer to the same real-world entity, is an essential task in data management. The prompt tuning paradigm for pre-trained language…

Fine-tuning a pre-trained model on a downstream task often degrades its original capabilities, a phenomenon known as "catastrophic forgetting". This is especially an issue when one does not have access to the data and recipe used to develop…

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

The Superficial Alignment Hypothesis posits that almost all of a language model's abilities and knowledge are learned during pre-training, while post-training is about giving a model the right style and format. We re-examine these claims by…

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…