相关论文: Do Prompts Reshape Representations? An Empirical S…

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token…

Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents…

Large Language Models (LLMs) with vast context windows offer new avenues for in-context learning (ICL), where providing many examples ("many-shot" prompting) is often assumed to enhance performance. We investigate this assumption for the…

Large language models (LLMs) have shown remarkable abilities in different fields, including standard Natural Language Processing (NLP) tasks. To elicit knowledge from LLMs, prompts play a key role, consisting of natural language…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

Large Language Models (LLMs) have shown remarkable capabilities in zero-shot learning applications, generating responses to queries using only pre-training information without the need for additional fine-tuning. This represents a…

In large language models (LLM)-based recommendation systems (LLM-RSs), accurately predicting user preferences by leveraging the general knowledge of LLMs is possible without requiring extensive training data. By converting recommendation…

Role-play prompting is known to steer the behavior of language models by injecting a persona into the prompt, improving their zero-shot reasoning capabilities. However, such improvements are inconsistent across different tasks or instances.…

Large language models are increasingly used as surrogate models for low-data optimization, but their optimizer-facing prediction and its uncertainty remain poorly understood. We study the surrogate belief elicited from an LLM under sparse…

Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks. Recently, prompt-based learning has emerged to leverage pre-trained models to be prompted to learn subsequent tasks without the…

System prompts are a central control mechanism in modern AI systems, shaping behavior across conversations, tasks, and user populations. Yet they are difficult to tune when feedback is available only as aggregate metrics rather than…

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…

Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts…

Large Language Models have recently been applied to text annotation tasks from social sciences, equalling or surpassing the performance of human workers at a fraction of the cost. However, no inquiry has yet been made on the impact of…

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…

Recently, scaling test-time compute on Large Language Models (LLM) has garnered wide attention. However, there has been limited investigation of how various reasoning prompting strategies perform as scaling. In this paper, we focus on a…

Modeling long histories plays a pivotal role in enhancing recommendation systems, allowing to capture user's evolving preferences, resulting in more precise and personalized recommendations. In this study we tackle the challenges of…

Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift…

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…

To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or 'soft prompts,' as a metric of conditional distance between a model and a target behavior.…