Pith. sign in

REVIEW 8 cited by

Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models

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 2310.20081 v1 pith:D62KHUTI submitted 2023-10-30 cs.CL cs.AIcs.IR

Integrating Summarization and Retrieval for Enhanced Personalization via Large Language Models

classification cs.CL cs.AIcs.IR
keywords userlanguagepersonalizationllmsretrievalapproachdatamodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Personalization, the ability to tailor a system to individual users, is an essential factor in user experience with natural language processing (NLP) systems. With the emergence of Large Language Models (LLMs), a key question is how to leverage these models to better personalize user experiences. To personalize a language model's output, a straightforward approach is to incorporate past user data into the language model prompt, but this approach can result in lengthy inputs exceeding limitations on input length and incurring latency and cost issues. Existing approaches tackle such challenges by selectively extracting relevant user data (i.e. selective retrieval) to construct a prompt for downstream tasks. However, retrieval-based methods are limited by potential information loss, lack of more profound user understanding, and cold-start challenges. To overcome these limitations, we propose a novel summary-augmented approach by extending retrieval-augmented personalization with task-aware user summaries generated by LLMs. The summaries can be generated and stored offline, enabling real-world systems with runtime constraints like voice assistants to leverage the power of LLMs. Experiments show our method with 75% less of retrieved user data is on-par or outperforms retrieval augmentation on most tasks in the LaMP personalization benchmark. We demonstrate that offline summarization via LLMs and runtime retrieval enables better performance for personalization on a range of tasks under practical constraints.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

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

  1. VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

    cs.AI 2026-05 unverdicted novelty 7.0

    VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.

  2. CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation

    cs.AI 2026-01 unverdicted novelty 7.0

    CARD uses style-based user clustering and implicit preference contrasts to enable efficient personalized text generation via lightweight decoding adjustments on frozen LLMs.

  3. CoPersona: Collaborative Persona Graphs for Robust LLM Personalization

    cs.IR 2026-07 unverdicted novelty 6.0

    CoPersona introduces a multiplex persona graph for facet-level peer alignment and a dual-branch retrieval-plus-reasoning architecture to improve LLM personalization under sparse and biased user interaction data.

  4. Preference-Aware Rubric Learning for Personalized Evaluation

    cs.CL 2026-05 unverdicted novelty 6.0

    PARL formulates personalized LLM evaluation as a learning problem that induces preference-aware rubrics from raw user histories via discriminative RL and self-validation.

  5. TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation

    cs.CL 2026-04 unverdicted novelty 6.0

    TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing t...

  6. Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization

    cs.IR 2026-06 unverdicted novelty 5.0

    TAP-PER encodes user preferences as lightweight learnable prefix embeddings that outperform prompt-based and adapter-based baselines on LaMP tasks with 130x fewer per-user parameters.

  7. Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization

    cs.CL 2026-06 unverdicted novelty 5.0

    PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.

  8. Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework

    cs.CL 2026-05 unverdicted novelty 5.0

    C-BPO personalizes LLMs via preference-calibrated binary signals and PU learning theory to isolate inter-user differences from shared task knowledge.