cs.AINov 14, 2026

CLEAR: Legible and Steerable Recommendation via Grounded Natural-Language Interests

Authors: Qi Guo, Reza Mirghaderi, Iordanis Fostiropoulos, David Fan, Yuchen Liu, Shiliang Tang, Lukasz Korycki, Golnaz Ghasemiesfeh, 

Abstract

Modern recommenders keep learned preferences in representations people cannot inspect or change. We present CLEAR (Controllable and Legible End-to-end Architecture for Recommendation), an end-to-end system deployed at Meta and built around an editable natural-language interest layer. CLEAR makes a ranked subset of inferred interests readable and stores accepted additions and suppressions as authoritative preference state. Behavioral grounding maps each inferred interest back to supporting events in the user's own history. The resulting interest object is also a serving address: its label and profile-conditioned rewrites drive lexical retrieval, its supporting events seed behavioral retrieval, its projection queries an embedding index, and its stable identity supports ranking, attribution, and exposure control. A fresh user declaration may precede behavioral support, so it enters through the same serving identity and initially draws candidates from topical retrieval. Ranking makes those candidates competitive, while a delivery controller observes attributable exposure and replenishes underexposed interests. Direct user review found that users rated about 88.5% of displayed interests accurate. In an offline benchmark using a shared evaluation protocol, the Specialized 3B generator reached 0.3967 mean-user F1@10, compared with 0.3633 for Gemini 2.5 Pro and 0.1911 for the prior generator. For a newly declared interest, a user-randomized cumulative ablation measured same-day delivery losses of 8.7 percentage points for added-interest ranking terms, 11.1 for reserved top-slot insertion, and 13.7 for interest-conditioned candidate sourcing, conditional on the tested removal sequence. CLEAR components have operated in production for over one year; the system spans four surfaces on Instagram and Facebook, with an interest layer people can inspect, correct, and use to direct recommendations.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation

    Aug 16, 2026Rui Wang, Jiazhou Wang, Zheng Wei +16Language Model SteeringRecommender Systems

  2. GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification

    Mar 31, 2026Iordanis Fostiropoulos, Muhammad Rafay Azhar, Abdalaziz Sawwan +8LLM EvaluationUser Modeling