← Back to all news
arXiv AI By Merieme Askour, Ayoub Merimi

When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization

Read the original on arXiv AI →

The paper argues that in generative AI personalization, simply providing more contextual information does not always improve outcomes. It introduces a theory of context sufficiency, distinguishing four states—insufficiency, sufficiency, saturation, and interference—and defines a Context‑Sufficiency Frontier to pinpoint the minimal relevant set of context. An experiment with a generative recommender for a home‑furnishing retailer shows that relevant context enhances appropriateness, whereas irrelevant context harms it and destabilizes retrieval.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 24

Benchmarking the Personalization Capabilities of Large Language Models

arXiv:2607. 20471v1 Announce Type: new Abstract: Personalization, the act of varying a message to induce action from a specific receiver while keeping sender, channel, and time fixed, has a long tradition in psychology and marketing as a two-party problem in which sender and receiver have independent objectives.

By Ashutosh Srivastava, Siddharth Yedlapati, Vinay Aggarwal, Yaman Kumar Singla, Shashwat Dixit, Jitendra Ajmera, Balaji Krishnamurthy
llmsagentsbenchmarks
More like this →
arXiv AI
Sep 15

Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain Itself

The paper presents a method for fine‑tuning a large language model (LLM) recommender to generate personalized, non‑harmful explanations for its recommendations. By training two LLM‑judge reward models and using constrained GRPO, the authors achieve a significant increase in the PASS rate for all three criteria, from 0.649 to 0.956 on their own judges and from 0.677 to 0.931 on an independent judge. The fine‑tuned model maintains its original recommendation performance, demonstrating that LLM‑based recommenders can be adapted to complex tasks without loss of effectiveness.

By Jiashu He, Emma Yanyang Kong, JJ Tan, David Fagnan
llmsagentsfine-tuningsafety
More like this →
arXiv Machine Learning
Aug 27

DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce Search

The paper introduces DCEO, a data‑driven framework that learns item‑level proxy scores directly aligned with long‑term user objectives in e‑commerce search. It aggregates these scores into a user‑level metric, measures alignment via relative causal effect, and uses an actor‑critic model to generate context‑dependent fusion weights for multiple objectives. Offline experiments and a 41‑day online A/B test show DCEO improves GMV by 0.36% over traditional proxies.

By Junzhao Zhang, Tao Zhang, Liren Yu, Feiyi Dong, Zhixuan Zhang, Dan Ou, Haihong Tang
safety
More like this →
arXiv Computation and Language
Oct 5

Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It

The paper investigates how large language model (LLM) agents exhibit source preference when selecting items in end‑to‑end search tasks across three domains. Across 12 agent models, each consistently favors certain sources and avoids others, even when items from disfavored sources better meet the user’s requirements. The study shows that revealing or hiding source identifiers influences selection, and that training rewards or missing information can create or mitigate these preferences.

By Jonghyun Song, Haewon Park, Jeonghoon Shim, Woojung Song, Yohan Jo
llmsagents
More like this →