# Reranking Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/reranking
> Markdown URL: https://aitinkerers.org/technologies/reranking.md
> Technology record last updated: 2026-02-26T13:23:22Z
> Generated: 2026-09-22T23:34:33Z

Reranking applies a Cross-Encoder to re-sort initial search results (top-k) by semantic relevance, boosting retrieval precision by 15 to 25 percent.

Standard vector search is efficient but lacks nuance: it compares fixed embeddings rather than the direct relationship between terms. Reranking fixes this by passing the query and the top 50 candidates through a specialized model (like Cohere Rerank 3) to score their actual relevance. This two-stage approach filters out the 'near-miss' results that often confuse LLMs. It is the most effective way to improve RAG performance without the overhead of fine-tuning an entire embedding model.

- Official technology site: https://cohere.com/rerank
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Repeated inference in practice](https://hamburg.aitinkerers.org/talks/rsvp_WxCKoC_z4CQ)

We use LLMs to identify which elements on a website are most relevant for changes based on a specific marketing strategy. This is a complex task, and due to the size of the prompt, the structured output from the LLM can sometimes be unstable and may lack precision and recall. By running multiple inferences and combining and reranking the outputs, we can achieve better stability and quality in the results.

- Event context: AI Tinkerers Hamburg - September 12 — 2024-09-12 — Hamburg
- Public talk page: https://hamburg.aitinkerers.org/talks/rsvp_WxCKoC_z4CQ

## Related Technologies

- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Inference](https://aitinkerers.org/technologies/inference) ([Markdown](https://aitinkerers.org/technologies/inference.md)) — 9 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [Output](https://aitinkerers.org/technologies/output) ([Markdown](https://aitinkerers.org/technologies/output.md)) — 2 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [Prompt](https://aitinkerers.org/technologies/prompt) ([Markdown](https://aitinkerers.org/technologies/prompt.md)) — 2 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos