# LinkedIn Uses LLM Scoring to Speed Profile Labeling

> A LinkedIn team reports that scoring candidates individually cut serving time and made labeling less sensitive to candidate order.

Oossa · 2026-10-28 · https://oossa.com/en/linkedin-uses-llm-scoring-to-speed-profile-labeling

A team of LinkedIn researchers describes replacing generated YES/NO lists with semantic scoring for profile qualification labels. Instead of generating a list of decisions, the system scores each candidate label using a model pass that avoids generating a full answer. The paper says its approach changed at most 0.01% of decisions when candidate order changed, and matched packed generation’s agreement with reference labels using about 4.7 times fewer training pairs.

A batching method called Multiple-Item Scoring raised throughput by 1.24 times offline and 1.9 times in model serving, under a one-second 99th-percentile latency target. The paper says the offline system uses a reusable Ray Data API and serving uses support in SGLang.

## The facts

- The paper reports 1.9× higher serving throughput under a one-second p99 latency target.
- The paper was published on arXiv on October 28, 2026.

## Why it matters

For teams labeling LinkedIn profiles, the reported gains could mean processing more candidates within the same serving-time target; the paper does not say whether the approach is available to other organizations.

## Sources & references

1. [From Generation to Scoring: Scaling LLM-Based Semantic Labeling at LinkedIn](https://arxiv.org/abs/2610.36383) – arXiv cs.IR, 2026-10-28

Last updated: 2026-10-28