User-LLM: Efficient LLM Contextualization with User Embeddings
- URL: http://arxiv.org/abs/2402.13598v1
- Date: Wed, 21 Feb 2024 08:03:27 GMT
- Title: User-LLM: Efficient LLM Contextualization with User Embeddings
- Authors: Lin Ning, Luyang Liu, Jiaxing Wu, Neo Wu, Devora Berlowitz, Sushant
Prakash, Bradley Green, Shawn O'Banion, Jun Xie
- Abstract summary: We propose User-LLM, a novel framework that leverages user embeddings to contextualize large language models (LLMs)
Our experiments on MovieLens, Amazon Review, and Google Local Review datasets demonstrate significant performance gains across various tasks.
- Score: 24.099604517203606
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) have revolutionized natural language processing.
However, effectively incorporating complex and potentially noisy user
interaction data remains a challenge. To address this, we propose User-LLM, a
novel framework that leverages user embeddings to contextualize LLMs. These
embeddings, distilled from diverse user interactions using self-supervised
pretraining, capture latent user preferences and their evolution over time. We
integrate these user embeddings with LLMs through cross-attention and
soft-prompting, enabling LLMs to dynamically adapt to user context. Our
comprehensive experiments on MovieLens, Amazon Review, and Google Local Review
datasets demonstrate significant performance gains across various tasks.
Notably, our approach outperforms text-prompt-based contextualization on long
sequence tasks and tasks that require deep user understanding while being
computationally efficient. We further incorporate Perceiver layers to
streamline the integration between user encoders and LLMs, reducing
computational demands.
Related papers
- Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
We train large language models (LLMs) that can ''interact to align''
We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures.
For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
arXiv Detail & Related papers (2024-10-04T17:48:29Z) - Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models [66.24055500785657]
Traditional turn-based chat systems prevent users from verbally interacting with system while it is generating responses.
To overcome these limitations, we adapt existing LLMs to listen users while generating output and provide users with instant feedback.
We build a dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions.
arXiv Detail & Related papers (2024-06-22T03:20:10Z) - TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation [16.93374578679005]
TokenRec is a novel framework for tokenizing and retrieving large-scale language models (LLMs) based Recommender Systems (RecSys)
Our strategy, Masked Vector-Quantized (MQ) Tokenizer, quantizes the masked user/item representations learned from collaborative filtering into discrete tokens.
Our generative retrieval paradigm is designed to efficiently recommend top-$K$ items for users to eliminate the need for auto-regressive decoding and beam search processes.
arXiv Detail & Related papers (2024-06-15T00:07:44Z) - Are you still on track!? Catching LLM Task Drift with Activations [55.75645403965326]
Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.
We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.
We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
arXiv Detail & Related papers (2024-06-02T16:53:21Z) - One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs)
We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
arXiv Detail & Related papers (2024-05-30T03:44:54Z) - Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors [25.086118164540974]
Large language models (LLMs) are used to improve the performance of click-through rate (CTR) prediction.
As user sequences grow longer, the current efficiency of LLMs is inadequate for training on billions of users and items.
We propose Behavior Aggregated Hierarchical (BAHE) to enhance the efficiency of LLM-based CTR modeling.
arXiv Detail & Related papers (2024-03-28T12:05:15Z) - Do LLMs Understand User Preferences? Evaluating LLMs On User Rating
Prediction [15.793007223588672]
Large Language Models (LLMs) have demonstrated exceptional capabilities in generalizing to new tasks in a zero-shot or few-shot manner.
We investigate various LLMs in different sizes, ranging from 250M to 540B parameters and evaluate their performance in zero-shot, few-shot, and fine-tuning scenarios.
arXiv Detail & Related papers (2023-05-10T21:43:42Z) - Low-code LLM: Graphical User Interface over Large Language Models [115.08718239772107]
This paper introduces a novel human-LLM interaction framework, Low-code LLM.
It incorporates six types of simple low-code visual programming interactions to achieve more controllable and stable responses.
We highlight three advantages of the low-code LLM: user-friendly interaction, controllable generation, and wide applicability.
arXiv Detail & Related papers (2023-04-17T09:27:40Z) - Check Your Facts and Try Again: Improving Large Language Models with
External Knowledge and Automated Feedback [127.75419038610455]
Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks.
This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
arXiv Detail & Related papers (2023-02-24T18:48:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.