Skip to content
Himalaya's LLM Self-Iterating Recommendation Parameters: Recall, Ranking, Re-ranking

Himalaya's LLM Self-Iterating Recommendation Parameters: Recall, Ranking, Re-ranking

Himalaya uses LLMs as user preference proxies to automatically optimize recommendation parameters across recall, ranking, and re-ranking stages, leveraging user context and long-term memory to generate personalized parameters via a parameter center, achieving significant metric gains for low-frequency users.

Ximalaya Technology Team
Ximalaya Technology Team
Ximalaya Technology Team

Background

Himalaya, a leading Chinese audio platform, uses a four-stage recommendation funnel: recall → coarse ranking → fine ranking → re-ranking. User feedback (clicks, completion) flows back for model iteration, forming a closed loop. Traditional models rely on user historical behavior as supervision signals, but audio scenarios suffer from three defects: sparse user interactions (lower than text/video), limited interest exploration due to vertical content categories and lack of personalized parameters, and high decision costs with delayed feedback signals (completion requires playback finish).

Overall Design: LLM as User Preference Proxy

The core idea: use LLMs to simulate user reasoning based on user context and long-term memory, generating personalized parameters for recall, ranking, and re-ranking stages. These parameters are deployed via the PBox parameter center, directly affecting online recommendations.

Core Modules

2.1 User Context & Long-Term Memory

User information is split into two layers:

Basic Attributes: Static user info (e.g., demographics) for initial profiling.

Historical Behavior: Sequences of clicks, plays, subscriptions, comments, shares, plus coarse category/tags. This enables LLM to reconstruct interest trajectories (e.g., news in morning, music at night).

2.2 LLM Reasoning Module

Key design choices:

Model Selection: Strong base LLM with good reasoning; adapted via prompt engineering without SFT.

Prompt Structure: Four-part template: role definition, task description, input specification, output constraints (JSON Schema for parseability).

Post-processing: Format validation, range checks (e.g., scores 0-1), anomaly filtering before writing to PBox.

Prompt example for LLM reasoning
Prompt example for LLM reasoning

2.3 PBox Parameter Center

PBox stores user-level personalized parameters covering the full funnel:

Recall: Personalized quota per channel, weight allocation, exploration quota.

Coarse Ranking: Paid content preference, quality preference.

Fine Ranking: Multi-objective fusion weights.

Re-ranking: Category diversity, content freshness, timeliness preferences.

PBox parameter center architecture
PBox parameter center architecture

Practice 1: LLM-Evaluated Personalized Recall Parameter Self-Iteration

Background

Recall channels include i2i, u2i, u2u, relevance, timeliness. Goal: quantify channel quality via LLM scoring to adjust quotas/weights.

Discriminative Evaluation Framework

Input: Candidate items (album/sound with title/tags) + user context/memory (hundreds of history records, long/short-term category preference scores).

Processing: LLM scores each item 1-5 based on match with user profiles.

Output: Scores aggregated per channel → channel quality profiles → increase quota/weight for good channels, decrease for poor, offline invalid ones. Parameters written to PBox.

Recall channel evaluation framework
Recall channel evaluation framework

Execution Flow

Get user's recall channel info.

Get user context & memory.

Feed both to LLM → output parameters to PBox.

PBox affects online recall.

Recommendation system returns results.

Recall parameter optimization flow
Recall parameter optimization flow

Concrete Example

Before: all users share default quotas (u2u:30, u2i:40, i2i:30) and weights (5.0, 3.0, 2.0). After LLM optimization per user:

User A: u2u match highest → quota 45, weight 6.0.

User B: i2i match highest → quota 55, weight 5.1, priority 3→1.

User C: u2i match highest → priority 2→1, weight 4.0.

Result: traffic shifts toward user-interest-aligned channels.

User-specific recall parameter changes
User-specific recall parameter changes

Results

Identified 10+ high-quality channels, 10+ potential, 20+ downgraded, 10+ taken offline. First quantitative evaluation of recall channels, enabling data-driven iteration.

Practice 2: LLM-Simulated Personalized Ranking Objective Fusion Self-Iteration

Background

Fine ranking uses multi-objective fusion: rank_score = ctr_bias + ctr_weight*ctr_score + dur_bias + dur_weight*dur_score + vipbuy_bias + vipbuy_weight*vipbuy_score (with scaling). Traditional tuning relies on manual A/B tests, slow and not personalized.

Fine ranking fusion formula
Fine ranking fusion formula

Evolution: v1 → v2 → v3

v1 (Generative): LLM directly outputs optimal weights. Failed: high-dimensional space, poor precision/stability.

v2 (Discriminative + User Profile): LLM scores ranked results; user profile added for preference simulation. Reduced complexity but parameter search still manual/grid.

v3 (Discriminative + User Profile + RL Parameter Optimization): LLM scores as reward signal → RL algorithm iterates parameters → closed loop: scoring → reward → parameter update → improvement. Final version deployed.

v3 architecture: discriminative scoring + RL optimization
v3 architecture: discriminative scoring + RL optimization

v3 Optimization Scheme

Input: Ranked candidate list (title, tags, paid info, tokenized title) + user context/memory (identity, search, play/like/subscribe sequences, aggregated interest tags).

Processing: LLM scores ranked list 0-1 (higher = more likely liked). Scores used as reward for RL parameter optimizer to search optimal weight combinations.

Output: Optimal per-user weights (ctr_weight, dur_weight, vipbuy_weight) written to PBox, affecting fine ranking.

Execution Flow

Get user's fine-ranking candidate logs.

RL optimizer proposes a parameter set.

Compute fusion scores, re-rank candidates.

Get user context/memory.

Feed re-ranked list + user info to LLM → score → feedback to RL optimizer.

Repeat until max iterations.

RL optimizer outputs optimal parameters → PBox → online ranking.

v3 execution flow diagram
v3 execution flow diagram

Concrete Example

Before: global defaults (ctr_weight 5.0, dur_weight 3.0, vipbuy_weight 2.0). After RL optimization per user:

User A (click-focused): 6.2, 3.4, 2.4.

User B (duration-focused): 4.1, 5.6, 1.2.

User C (paid-conversion-focused): 3.3, 2.2, 4.8.

User-specific fine-ranking weight changes
User-specific fine-ranking weight changes

Results

v3 deployed for low-frequency and veteran users. Low-frequency users: PVCTR +10.83%, avg play duration +12.16%, retention positive trend. Retention gains stabilize over time.

v3 online experiment results
v3 online experiment results

Practice 3: LLM-Optimized Personalized Re-ranking Business Weight Self-Iteration

Background

Re-ranking balances precision and diversity. Global uniform dispersion parameters fail: some users prefer deep vertical content (students → exam courses), others prefer cross-category exploration (professionals → career + emotional + finance). PBox enables personalized dispersion parameters, but manual tuning doesn't scale.

Re-ranking personalization motivation
Re-ranking personalization motivation

Optimization Scheme

Input: User behavior sequences (hundreds of records), user summary profile, basic info.

Processing: LLM infers preferences, scores three dimensions: category diversity (0-1), sound timeliness (0-1), album timeliness (0-1). Also extracts primary/exploration interest categories with intensities (0.1-1.0). Timeliness scores mapped to high/medium/low tiers: high [0.8,1.0], medium [0.6,0.8), low [0,0.6).

Output: Per-user re-ranking parameters (diversity, sound timeliness, album timeliness scores + interest categories/intensities) → PBox → affects re-ranking.

Execution Flow

Get user context & memory.

LLM infers preferences.

Aggregate & filter preferences → PBox → online re-ranking.

Recommendation system returns results.

Re-ranking parameter optimization flow
Re-ranking parameter optimization flow

Concrete Example

Before: global defaults (diversity 0.1, timeliness 0.9). After LLM:

User A: diversity 0.1→0.3, timeliness 0.9→0.7.

User B: diversity 0.1→0.6, timeliness 0.9→0.4 (strongest exploration).

User C: diversity 0.1→0.2, timeliness 0.9→0.8 (still timeliness-oriented).

User-specific re-ranking parameter changes
User-specific re-ranking parameter changes

Results

10+ LLM-optimized re-ranking parameter sets fully online, covering sounds, albums, cards. All full-traffic experiments show stable positive retention lift. For recall users, timeliness+diversity parameters yield retention improvements at the per-mille level.

Summary & Future Directions

Three practices validate LLM-based user simulation for recommendation parameter optimization, forming a closed loop: simulation → optimization → verification.

Recall: Quantitative channel evaluation (10+ identified each for quality/potential/downgrade/offline), enabling data-driven iteration.

Ranking: v3 (discriminative + profile + RL) deployed; low-frequency users: PVCTR +10.83%, duration +12.16%, retention positive.

Re-ranking: 10+ parameter sets online, stable retention gains, per-mille improvements for recall users.

Future work:

Integrate commercial goals (ad revenue, paid conversion) via multi-objective LLM optimization.

Expand parameter types and granularity across full funnel (recall, coarse, fine, re-ranking) for true per-user personalization.

Auto-research: feed platform-specific knowledge (content taxonomy, user behavior, audio specifics, iteration history) to LLM alongside frontier papers for faster strategy research and tuning.

Original Source

Signed-in readers can open the original source through BestHub's protected redirect.

Sign in to view source
Republication Notice

This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactadmin@besthub.devand we will review it promptly.

LLMRecommendation SystemRankingRecallUser ModelingSelf-IterationRe-rankingParameter OptimizationHimalayaPBox
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.