相关论文: Can Gradient Descent Simulate Prompting?

LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. Despite the success, the underlying mechanism of this…

Adapting pre-trained models to open classes is a challenging problem in machine learning. Vision-language models fully explore the knowledge of text modality, demonstrating strong zero-shot recognition performance, which is naturally suited…

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Large language models encode impressively broad world knowledge in their parameters. However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life." While online fine-tuning can reduce this…

Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial…

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt…

We introduce $\mathbf{G}$radient Descent with $\mathbf{A}$daptive $\mathbf{M}$omentum $\mathbf{S}$caling ($\mathbf{Grams}$), a novel optimization algorithm that decouples the direction and magnitude of parameter updates in deep learning.…

Prompt engineering for large language models (LLMs) is often a manual time-intensive process that involves generating, evaluating, and refining prompts iteratively to ensure high-quality outputs. While there has been work on automating…

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…

In Recurrent Neural Networks (RNNs), encoding information in a suboptimal or erroneous way can impact the quality of representations based on later elements in the sequence and subsequently lead to wrong predictions and a worse model…

This research investigates prompt designs of evaluating generated texts using large language models (LLMs). While LLMs are increasingly used for scoring various inputs, creating effective prompts for open-ended text evaluation remains…

Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research primarily emphasizes the importance of adapting prompts to…

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

The use of Large Language Models (LLMs) for simulating user behavior in the domain of Interactive Information Retrieval has recently gained significant popularity. However, their application and capabilities remain highly debated and…

The integration of contextual embeddings into the optimization processes of large language models is an advancement in natural language processing. The Context-Aware Neural Gradient Mapping framework introduces a dynamic gradient adjustment…

Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data. For low-resource scenarios, prompt-based…

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new reasoning capabilities by generating a scratch-pad before…

Large Language Models (LLMs) often generate substantively relevant content but fail to adhere to formal constraints, leading to outputs that are conceptually correct but procedurally flawed. Traditional prompt refinement approaches focus on…

As the post-training of large language models (LLMs) advances from instruction-following to complex reasoning tasks, understanding how different data affect finetuning dynamics remains largely unexplored. In this paper, we present a…

Auto-evaluating language models (LMs), i.e., using a grader LM to evaluate the candidate LM, is an appealing way to accelerate the evaluation process and the cost associated with it. But this presents a paradox: how can we trust the grader…