How to Fight Clickbait: Meta, LinkedIn & YouTube Case Studies

Author (article How to Fight Clickbait: Meta, LinkedIn & YouTube Case Studies): In March 2026, LinkedIn replaced those systems with a single retrieval model built on a fine-tuned version of Meta's LLaMA-3. The model acts as a dual encoder, converting both members and posts into one shared embedding space. It serves the entire feed through nearest-neighbor search at sub-50-millisecond latency... A language model processes text, while a recommendation system runs on structured features such as view counts, engagement rates, work history, and post metadata. LinkedIn bridged this with a prompt library that converts structured fields into templated text sequences the model can process... When the team fed raw popularity counts directly into the prompts, the numbers had almost no correlation with the model's relevance scores, because large integers entered the model as arbitrary tokens. Converting each count into a ranked bucket, expressed as a percentage that the model could process in context, raised the correlation sharply and improved retrieval accuracy by roughly fifteen percent. The takeaway from this is that the model is often the part that works, and the surrounding representation of the data is where the real effort goes.

Author (article How to Fight Clickbait: Meta, LinkedIn & YouTube Case Studies): Meta arranges Instagram's recommendation system as a multi-stage funnel, consisting of an ecosystem of more than a thousand models supporting it. Candidates pass through a sequence of stages, and each stage applies a more expensive model to a smaller set of surviving candidates... In Meta's approach, the late-stage model predicts many possible user actions at once, and a value model combines those predictions into a single score. That combination adds weight for positive actions, such as a likely save, and subtracts weight for predicted negative actions, such as a "See Fewer Posts Like This" tap. The basic objective of this extends past raw engagement to include signals about content a user would prefer to avoid... Many competing objectives, including engagement, diversity, integrity, and creator fairness, are easier to tune and audit as separate stages than as one model. Of course, the cost to this is operational complexity, which is the exact complexity LinkedIn set out to reduce.

Author (article How to Fight Clickbait: Meta, LinkedIn & YouTube Case Studies): The system, called PLUM, assigns every video a Semantic ID, a short sequence of discrete codes derived from the video's own content. Videos with similar content receive similar codes, so the identifier carries information about the item rather than acting as a random label. PLUM then adapts a pretrained language model (from the Gemini family) by adding these Semantic IDs to its vocabulary and continuing to train it on video metadata and user activity. After this adaptation, the model performs retrieval as a generation task. Given a user's recent history, it produces the Semantic IDs of the videos that the user is likely to watch next... This approach, however, introduces a failure mode that the index-based designs avoid, which is generating an identifier that maps to no video, and PLUM reports keeping that rate below five percent after fine-tuning. Measured against the previous production system, PLUM surfaced a far wider range of long-tail videos, and on YouTube Shorts, it raised panel click-through by 4.96 percent.