With the rise of large language models (LLMs) for flexibly processing information as strings, a natural application is regression, specifically by preprocessing string representations into LLM embeddings as downstream features for metric prediction. In this paper, we provide one of the first comprehensive investigations into embedding-based regression and demonstrate that LLM embeddings as features can be better for high-dimensional regression tasks than using traditional feature engineering. This regression performance can be explained in part due to LLM embeddings over numeric data inherently preserving Lipschitz continuity over the feature space. Furthermore, we quantify the contribution of different model effects, most notably model size and language understanding, which we find surprisingly do not always improve regression performance.

In the past two years, large language models (LLMs) have achieved rapid development and demonstrated remarkable emerging capabilities. Concurrently, with powerful semantic understanding and reasoning capabilities, LLMs have significantly empowered the rapid advancement of the recommendation system field. Specifically, in news recommendation (NR), systems must comprehend and process a vast amount of clicked news text to infer the probability of candidate news clicks. This requirement exceeds the capabilities of traditional NR models but aligns well with the strengths of LLMs. In this paper, we propose a novel NR algorithm to reshape the news model via LLM Embedding and Co-Occurrence Pattern (LECOP). On one hand, we fintuned LLM by contrastive learning using large-scale datasets to encode news, which can fully explore the semantic information of news to thoroughly identify user preferences. On the other hand, we explored multiple co-occurrence patterns to mine collaborative information. Those patterns include news ID co-occurrence, Item-Item keywords co-occurrence and Intra-Item keywords co-occurrence. The keywords mentioned above are all generated by LLM. As far as we know, this is the first time that constructing such detailed Co-Occurrence Patterns via LLM to capture collaboration. Extensive experiments demonstrate the superior performance of our proposed novel method

This paper presents the Customer Experience (CX) Simulator, a We focus on the potential of LLMs to solve this issue. LLMs have novel framework designed to assess the effects of untested webmarketing been applied not only for natural language processing tasks [12] but campaigns through user behavior simulations. The proposed also for common sense reasoning in multi-modal data [34]. We believe framework leverages large language models (LLMs) to represent that the ability of LLMs, especially to represent the high-level various events in a user's behavioral history, such as viewing an semantics of complex event descriptions with compact embedded item, applying a coupon, or purchasing an item, as semantic embedding vectors (i.e., LLM embeddings) [15], can also be advantageous for vectors. We train a model to predict transitions between events web marketing applications from their LLM embeddings, which can even generalize to unseen In this work, we propose a novel framework named CXSimulator events by learning from diverse training data.