REVIEW 14 cited by
User-LLM: Efficient LLM Contextualization with User Embeddings
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Large language models (LLMs) have achieved remarkable success across various domains, but effectively incorporating complex and potentially noisy user timeline data into LLMs remains a challenge. Current approaches often involve translating user timelines into text descriptions before feeding them to LLMs, which can be inefficient and may not fully capture the nuances of user behavior. Inspired by how LLMs are effectively integrated with images through direct embeddings, we propose User-LLM, a novel framework that leverages user embeddings to directly contextualize LLMs with user history interactions. These embeddings, generated by a user encoder pretrained using self-supervised learning on diverse user interactions, capture latent user behaviors and interests as well as their evolution over time. We integrate these user embeddings with LLMs through cross-attention, enabling LLMs to dynamically adapt their responses based on the context of a user's past actions and preferences. Our approach achieves significant efficiency gains by representing user timelines directly as embeddings, leading to substantial inference speedups of up to 78.1X. Comprehensive experiments on MovieLens, Amazon Review, and Google Local Review datasets demonstrate that User-LLM outperforms text-prompt-based contextualization on tasks requiring deep user understanding, with improvements of up to 16.33%, particularly excelling on long sequences that capture subtle shifts in user behavior. Furthermore, the incorporation of Perceiver layers streamlines the integration between user encoders and LLMs, yielding additional computational savings.
Forward citations
Cited by 14 Pith papers
-
Before You Say It: Anticipating Verbal Behavior from Longitudinal Everyday Conversations with LLMs
A pattern-conditioned LLM method predicts a person's next verbal communicative intent from longitudinal everyday conversations, beating non-personalized baselines by up to 29% in an LLM-judge evaluation.
-
Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces
A five-stage LLM pipeline infers explainable beliefs and personas from browsing traces, and these inferred profiles match or beat interview-derived profiles on several downstream prediction tasks.
-
The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs
Adding user memory to LLMs degrades their emotional-intelligence test scores and systematically disadvantages marginalized user profiles.
-
Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization
An EM-type algorithm jointly learns interpretable mnemonic rules and learner/kanji traits, yielding modest cold-start gains over fine-tuning for kanji mnemonic generation.
-
Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals
A 7B model trained with synthetic reasoning demonstrations plus reinforcement learning infers explicit user preference descriptions from behavioral signals, improving personalized response judging and generation.
-
CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents
CAIM, a cognitive-AI-inspired memory framework with ontology-based tagging and relevance filtering, improves retrieval and response correctness for LLM assistants on the Generated Virtual Dataset compared with MemoryB...
-
PRECISE: Pre-training Sequential Recommenders with Collaborative and Semantic Information
A mixture-of-experts fusion of trainable LLM semantic embeddings with collaborative item IDs, followed by universal-then-targeted pre-training, improves sequential recommendation on Amazon and WeChat.
-
Large Behavior Model: A Promptable Digital Twin of the Retail Customer
Grounding an LLM in verbalized transaction histories via Person–Environment prompting, continued pre-training, SFT, and GRPO yields stronger retail decision simulation than frontier models, with partial cross-domain transfer.
-
Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendation
Molar combines multimodal LLM item embeddings with a contrastive post-alignment to an ID-based sequential recommender, reporting improved NDCG and Recall on three datasets.
-
Enhancing LLMs through human feedback: a journey towards self-improvement
An auxiliary feedback RAG continuously ingests classified human feedback to iteratively raise a primary RAG system’s answer accuracy and relevance.
-
Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models
E2P projects pre-computed user embeddings into a single soft prefix token for frozen LLMs, reporting gains on four personalization tasks, though its reproduction scripts write zero embeddings.
-
A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms
A survey that organizes foundation-model recommender systems into feature-based, generative, and agentic paradigms and reviews tasks, empirical results, and open challenges.
-
Intelligent Interaction Strategies for Context-Aware Cognitive Augmentation
A small qualitative study in an exhibition suggests that LLM cognitive augmentation should be context-aware, socially adaptive, and able to shift between real-time assistance and post-visit knowledge organization.
-
Challenges in Guardrailing Large Language Models for Science
A position paper proposing a guardrail framework with four dimensions (trustworthiness, ethics & bias, safety, legal) and implementation strategies for scientific LLM use.
Discussion (0). Continue with ORCID to comment.