Pith. sign in

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

arxiv 2402.13598 v2 pith:BA2PM3KC submitted 2024-02-21 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords userllmsembeddingscaptureuser-llmbehaviorcontextualizationdirectly
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Before You Say It: Anticipating Verbal Behavior from Longitudinal Everyday Conversations with LLMs

    cs.HC 2026-08 conditional novelty 6.0 of 10

    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.

  2. Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic Intelligent Interfaces

    cs.AI 2026-08 conditional novelty 6.0 of 10

    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.

  3. The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs

    cs.AI 2025-10 conditional novelty 6.0 of 10

    Adding user memory to LLMs degrades their emotional-intelligence test scores and systematically disadvantages marginalized user profiles.

  4. Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximization

    cs.CL 2025-07 conditional novelty 6.0 of 10

    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.

  5. Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals

    cs.CL 2025-05 conditional novelty 6.0 of 10

    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.

  6. CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents

    cs.AI 2025-05 conditional novelty 6.0 of 10

    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...

  7. PRECISE: Pre-training Sequential Recommenders with Collaborative and Semantic Information

    cs.IR 2024-12 conditional novelty 6.0 of 10

    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.

  8. Large Behavior Model: A Promptable Digital Twin of the Retail Customer

    cs.AI 2026-07 conditional novelty 5.0 of 10

    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.

  9. Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendation

    cs.IR 2024-12 conditional novelty 5.0 of 10

    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.

  10. Enhancing LLMs through human feedback: a journey towards self-improvement

    cs.IR 2026-07 unverdicted novelty 4.0 of 10

    An auxiliary feedback RAG continuously ingests classified human feedback to iteratively raise a primary RAG system’s answer accuracy and relevance.

  11. Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models

    cs.CL 2025-05 reject novelty 4.0 of 10

    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.

  12. A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms

    cs.IR 2025-04 conditional novelty 4.0 of 10

    A survey that organizes foundation-model recommender systems into feature-based, generative, and agentic paradigms and reviews tasks, empirical results, and open challenges.

  13. Intelligent Interaction Strategies for Context-Aware Cognitive Augmentation

    cs.HC 2025-04 conditional novelty 3.0 of 10

    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.

  14. Challenges in Guardrailing Large Language Models for Science

    cs.AI 2024-11 conditional novelty 3.0 of 10

    A position paper proposing a guardrail framework with four dimensions (trustworthiness, ethics & bias, safety, legal) and implementation strategies for scientific LLM use.

Pith tools