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
Figure 1: Generate, inspect, edit, retrieve, and re-rank through one interest layer. An LLM proposes interests from recent activity, and behavioral grounding checks inferred entries before they enter the displayed profile. The user suppresses Reality TV and adds Painting. A fresh addition receives a stable serving identity immediately even when it has no prior support events; topical retrieval adds Painting candidates, and ranking makes them competitive in the next feed. Subsequent responses return through ordinary interaction history. Rankings are schematic.
Figure 2: Grounding gives one editable interest four retrieval addresses and a stable serving identity. The display label becomes a lexical query, profile-conditioned rewrites expand that query, inferred interests retain behavioral support for trigger-to-item retrieval, the interest projection becomes an embedding query, and the user–interest identity can condition generative retrieval and cached supply. Candidates merge, pass a hard topicality gate, and enter ranking. Attribution preserves the same interest identity for delivery control; explicit negative state remains in the policy path.
Study
Metric
Result
A. Legibility and profile quality
Direct review
Displayed interests rated accurate
≈ 88.5%
Specialized 3B generator
Mean-user F1@10 / P@10 / R@10 / F1@all
0.3967 / 0.8067 / 0.2901 / 0.5493
Gemini 2.5 Pro
Mean-user F1@10 / P@10 / R@10 / F1@all
0.3633 / 0.7982 / 0.2568 / 0.7051
Prior production generator
Mean-user F1@10 / P@10 / R@10 / F1@all
0.1911 / 0.5692 / 0.1281 / 0.4281
B. Steerability
Table 1: Legibility and steerability. Direct review and system-level rows report measured levels; replenishment and volume regulation report relative changes. Direct review is descriptive, and the generator comparison is an offline benchmark using a shared history format, user-validated reference, and semantic judge. Responsiveness and prevalence are one-week Instagram production averages; topicality is the most recent twice-weekly judge run. Responsiveness is attributed matching delivery on the day of the edit; topicality is scored by a judge independent of the serving gate and validated against human labels (Section 6.3 ). Replenishment is a separate user-randomized comparison against the prior age-limited policy. Volume regulation compares real-time per-interest accounting and recalibrated dampening with prior daily accounting. Component-level contrasts appear in Table 3 .
Figure 3: Grounding precision–coverage trade-off. Curves show threshold sweeps for two single-channel embedding matchers. The deployed text-plus-media union is evaluated separately and summarized below the plot. Support precision concerns judged event–interest matches; coverage counts deduplicated history events. Table A2 reports the selected operating-point results.
Metric
Observed comparison
Same-surface reference: attributed vs. other recommended
Like rate
11.55% attributed vs. 9.90% other recommended; +1.65 pp
Positive-to-negative content-control tap ratio
6.44 attributed vs. 2.95 other recommended; 2.2 ×
Three-second skip rate
+1.6 pp on attributed recommendations
Dwell per impression
− 10% on attributed recommendations
Cross-surface stated-intent reference: attributed vs. search-result videos
Table 2: Descriptive reception against recommendation and stated-intent references. Among viewers holding at least one declared interest, the first block compares attributed and other recommendations on Instagram Reels. The second uses videos viewed through Instagram Search as a cross-surface stated-intent reference.
A. Positive addition
Layer removed
Loss in same-day delivery
Interest-conditioned candidate sourcing
13.7 pp
Forced top-slot insertion
11.1 pp
Added-interest ranking boosts
8.7 pp
All layers removed
33.5 pp
B. Negative suppression
Table 3: Controlled serving-component effects for positive and negative edits. Panel A is a five-arm user-randomized cumulative ablation of Instagram’s positive-addition delivery layers. Component rows report consecutive-arm delivery losses in the tested removal order; the full-stack row reports the outer-arm contrast. All reported randomized serving-component comparisons have p<0.01 . The endpoint uses a slightly narrower definition than the same-day responsiveness in Table 1 and is read as an approximation of it. Because the arms are nested, the decomposition is specific to this removal order and is not an order-free attribution. Negative filtering and suppression produced no measurable change on this positive-addition endpoint and are omitted from Panel A. Panel B is a separate user-randomized suppression experiment; lower suppressed-interest reappearance is better.
Appendix figures & tables7 assets
Supplementary material from the paper’s appendix.
Appendix
Finding
Result
Viewed without personal interest
41% of rejections
Transient interest
29% of rejections
No personal interest
21% of rejections
Other responses
≈ 9% of rejections
Appendix
Table A1: Why profile corrections are necessary. Reasons users gave for rejecting a displayed interest. Categories sum to approximately 100% after rounding.
Evaluation
Configuration
Metric
Result
Profile filtering frontier: increasingly strict support
Profile filtering
Unfiltered candidates
Precision
69.9%
Profile filtering
Unfiltered candidates
Reference recall
46.2%
Profile filtering
At least one supporting event
Precision
74.5%
Profile filtering
At least one supporting event
Reference recall
41.5%
Profile filtering
At least three supporting events (selected)
Precision
77.4%
Appendix
Table A2: Grounding quality and coverage. Profile filtering forms a whole-profile precision–recall frontier: increasingly strict support retains fewer interests while raising precision. The selected three-event point prioritizes whole-profile precision for displayed interests. Event grounding separately evaluates retrieved history-event and inferred-interest pairs.
Configuration
Metric
Result
Full regeneration (1,000 users)
Whole-profile precision / recall / F1
0.6375 / 0.1101 / 0.1819
Incremental merging (1,000 users)
Whole-profile precision / recall / F1
0.6501 / 0.1135 / 0.1867
Incremental inference versus preceding history budget
Estimated accelerator requirement
35% lower
Appendix
Table A3: Incremental profile updates. Full regeneration and incremental merging use the same fixed reference; whole-profile precision, recall, and F1 are reported, with p<0.01 for the incremental comparison. Capacity reduction is measured against the preceding history-budget configuration.
Model
F1@all
F1@10
Relative inference cost
Specialized 3B
0.5493
0.3967
1 ×
Gemini 2.5 Pro
0.7051
0.3633
216 ×
Appendix
Table A4: F1@all, F1@10, and inference cost. Costs use the historical common maximum-history input basis with the 3B cost reference normalized to 1 × .
Lever
Metric
Result
Grouped versus uncompressed history
Prompt tokens
39.5% fewer
History budgeting versus unbudgeted history
Estimated accelerator requirement
38.9% lower
Per-string versus per-user annotation
Logical annotation requests
≈ 98% fewer
Updated versus preceding annotation pipeline
Throughput per accelerator
+145.5%
Parallel versus serial request-time attribution
Chunk-0 server latency
≈ 5 ms lower
Deployment
Enabled surfaces / platforms (Instagram and Facebook)
4 / 2
Appendix
Table A5: Deployment efficiency and breadth. Each row has its own baseline; deployment counts enabled surfaces across Instagram and Facebook.
State
Entry condition
Persistence and precedence
Serving effect
Inferred
Generated from activity and retained after behavioral support and policy checks
Refreshed with the inferred profile; may expire when support decays
Available to profile ranking, retrieval, attribution, and display selection
Explicit addition
Accepted normalized user text; prior behavioral support is optional
Stored separately from inference and persists until the user changes it
Creates an authoritative positive interest identity for topical supply and ranking
Explicit promotion
A user promotes an existing normalized identity
Explicit preference outranks later inferred state
Raises the priority of matching candidates through the shared identity
Explicit removal or suppression
A user removes an entry or requests less of its normalized identity
Stored as explicit state and not overwritten by later inference
Excludes the entry from the served profile or applies the corresponding negative serving path
Appendix
Table A6: State and action contract. Verified state transitions used by profile construction and serving.
Study
Treatment and comparison
Analysis population / unit
Endpoint and uncertainty
Direct review
One deployed displayed profile; descriptive review
7,261 displayed interests from 393 users; pooled over entries
Entry rated accurate; descriptive percentage
Generator benchmark
Specialized 3B, Gemini 2.5 Pro, and prior generator; shared history format, reference, and judge
Mean-user F1@10 / P@10 / R@10 / F1@all; reported model means
System-level steerability
Deployed-system descriptive measurements
Newly declared interest, eligible user, and sampled attributed impression
79.6% responsiveness, 82.6% prevalence, and 87.2% independently judged topicality
Instagram Reels reception
Attributed versus other recommendations for the declared-interest cohort
Delivered impressions and content-control actions
Selected levels and contrasts
Instagram Search reference
Attributed recommendations versus search-result videos
Delivered impressions; common user sample for skips
Relative like and dwell; percentage-point skip contrast
Serving-layer stack ablation
Four cumulative removal arms and production control (Appendix B )
Eligible positive-interest lifecycle
Attributed matching delivery same day and within 16 impressions; p<0.01
Appendix
Table A7: Study contracts for Tables 1–3. All online component comparisons are randomized by user. Replenishment and volume-regulation values show relative changes with bracketed uncertainty intervals.