Kanon 2 Reranker: the most powerful reranker for legal RAG
โข
6
AI & ML interests
We build legal AI models for legal tech firms that help them ship smarter products, faster.
Recent Activity
Papers
View all Papers
Articles
umarbutlerย
updated a collection 2 days ago
umarbutlerย
published a dataset 2 days ago
umarbutlerย
updated a dataset 2 days ago
abdurrahmanbutlerย
updated a dataset 3 days ago
umarbutlerย
updated a Space 6 days ago
abdurrahmanbutlerย
posted an
update 6 days ago
Post
175
Isaacus just shipped a new state-of-the-art model, this time focused on reranking for legal RAG.
Although Kanon 2 Embedder already represents the frontier of legal-domain retrieval, we know that not everyone is ready to re-embed their entire corpus. We also knew there was still accuracy left on the table for teams handling highly sensitive legal work.
Enter Kanon 2 Reranker: the worldโs best legal reranking model.
We tested it across both production RAG pipelines and standalone retrieval tasks, and the results were remarkable.
Not only does it outperform the competition in a category where there are still very few serious alternatives, it also delivers major retrieval accuracy gains over our standalone embedder. Those improvements translated into exceptional downstream performance.
In our final test, we compared Voyage AI by MongoDB 2.5 Rerank with Kanon 2 Reranker on Legal RAG Bench, using identical embedding models, generative models, and pipeline hyperparameters. The only difference was the reranker.
The result: Kanon 2 Reranker decisively outperformed Voyage 2.5 Rerank.
On holdout questions, the head-to-head margin was one of the most extreme we have seen: for every 1 question Voyage got right and we got wrong, there were 6 questions we got right and Voyage got wrong.
We share an example in the blog post where Voyage Rerank actually underperforms Kanon 2 Embedder on its own, delivering the wrong context to the LLM. In that case, not using a reranker at all would have led to the correct answer.
All in all, Iโm immensely proud of the performance gains weโve achieved.
But as we always say, the best benchmark is your own data.
So redeem your free credits, give Kanon 2 Reranker a try, and see firsthand the difference our models can make:
https://huggingface.co/blog/isaacus/kanon-2-reranker
Although Kanon 2 Embedder already represents the frontier of legal-domain retrieval, we know that not everyone is ready to re-embed their entire corpus. We also knew there was still accuracy left on the table for teams handling highly sensitive legal work.
Enter Kanon 2 Reranker: the worldโs best legal reranking model.
We tested it across both production RAG pipelines and standalone retrieval tasks, and the results were remarkable.
Not only does it outperform the competition in a category where there are still very few serious alternatives, it also delivers major retrieval accuracy gains over our standalone embedder. Those improvements translated into exceptional downstream performance.
In our final test, we compared Voyage AI by MongoDB 2.5 Rerank with Kanon 2 Reranker on Legal RAG Bench, using identical embedding models, generative models, and pipeline hyperparameters. The only difference was the reranker.
The result: Kanon 2 Reranker decisively outperformed Voyage 2.5 Rerank.
On holdout questions, the head-to-head margin was one of the most extreme we have seen: for every 1 question Voyage got right and we got wrong, there were 6 questions we got right and Voyage got wrong.
We share an example in the blog post where Voyage Rerank actually underperforms Kanon 2 Embedder on its own, delivering the wrong context to the LLM. In that case, not using a reranker at all would have led to the correct answer.
All in all, Iโm immensely proud of the performance gains weโve achieved.
But as we always say, the best benchmark is your own data.
So redeem your free credits, give Kanon 2 Reranker a try, and see firsthand the difference our models can make:
https://huggingface.co/blog/isaacus/kanon-2-reranker
umarbutlerย
published an
article 6 days ago
Article
Kanon 2 Reranker: the most powerful reranker for legal RAG
โข
6
umarbutlerย
updated a dataset 8 days ago
umarbutlerย
updated a dataset 9 days ago
umarbutlerย
posted an
update 10 days ago
Post
1922
This awesome visualization by @abdurrahmanbutler tracks how reliant the High Court of Australia has been on UK precedents over time.
Back in the early 1900s, up to 70% of citations in High Court decisions were from the UK. Today, that number sits around 20%.
This change seems to have happened gradually as Australia gained more and more independence from the UK, culminating in the Australia Acts of 1986, where we see a nice bump in the proportion of Australian cases cited.
These insights would not be possible without our latest legal AI model, Kanon 2 Enricher, which we used to extract dates and citations from High Court decisions in isaacus/open-australian-legal-corpus and categorize citations by jurisdiction. You can learn about Kanon 2 Enricher here: https://isaacus.com/blog/kanon-2-enricher.
Back in the early 1900s, up to 70% of citations in High Court decisions were from the UK. Today, that number sits around 20%.
This change seems to have happened gradually as Australia gained more and more independence from the UK, culminating in the Australia Acts of 1986, where we see a nice bump in the proportion of Australian cases cited.
These insights would not be possible without our latest legal AI model, Kanon 2 Enricher, which we used to extract dates and citations from High Court decisions in isaacus/open-australian-legal-corpus and categorize citations by jurisdiction. You can learn about Kanon 2 Enricher here: https://isaacus.com/blog/kanon-2-enricher.
abdurrahmanbutlerย
updated a dataset 10 days ago
umarbutlerย
updated a dataset 10 days ago
abdurrahmanbutlerย
posted an
update 13 days ago
Post
2574
๐ ๐๐ป๐๐ฟ๐ผ๐ฑ๐๐ฐ๐ถ๐ป๐ด ๐๐ฎ๐ป๐ผ๐ป ๐ฎ ๐๐ป๐ฟ๐ถ๐ฐ๐ต๐ฒ๐ฟ: ๐๐ต๐ฒ ๐๐ผ๐ฟ๐น๐ฑโ๐ ๐ณ๐ถ๐ฟ๐๐ ๐ต๐ถ๐ฒ๐ฟ๐ฎ๐ฟ๐ฐ๐ต๐ถ๐ฐ๐ฎ๐น ๐ด๐ฟ๐ฎ๐ฝ๐ต๐ถ๐๐ถ๐๐ฎ๐๐ถ๐ผ๐ป ๐บ๐ผ๐ฑ๐ฒ๐น
Today weโre publicly releasing Kanon 2 Enricher, and with it, an entirely new class of AI model that weโre calling a hierarchical graphitization model.
This is fundamentally different from both universal extraction models and generative models.
As a hierarchical graphitization model, Kanon 2 Enricher natively outputs a ๐ธ๐ป๐ผ๐๐น๐ฒ๐ฑ๐ด๐ฒ ๐ด๐ฟ๐ฎ๐ฝ๐ต rather than tokens, which makes it architecturally incapable of hallucinating or inventing text that wasnโt present in the input.
What that enables in practice is unlike any other model or ML architecture on the market:
โข ๐ก๐ผ ๐ต๐ฎ๐น๐น๐๐ฐ๐ถ๐ป๐ฎ๐๐ถ๐ผ๐ป๐ ๐ค
It cannot hallucinate. All references and links are stored as spans, meaning exact character offsets anchored to the original text.
โข ๐๐ถ๐ฒ๐ฟ๐ฎ๐ฟ๐ฐ๐ต๐ถ๐ฐ๐ฎ๐น ๐๐ฒ๐ด๐บ๐ฒ๐ป๐๐ฎ๐๐ถ๐ผ๐ป, ๐ป๐ผ๐ ๐ท๐๐๐ ๐ฒ๐ ๐๐ฟ๐ฎ๐ฐ๐๐ถ๐ผ๐ป ๐
It deconstructs a documentโs full nested hierarchy, down to chapters, sections, clauses, schedules, signatures, and even singular sentences, and classifies each span with dozens of contextual features.
โข ๐๐ป๐๐ถ๐๐ ๐ฒ๐ ๐๐ฟ๐ฎ๐ฐ๐๐ถ๐ผ๐ป, ๐ฑ๐ถ๐๐ฎ๐บ๐ฏ๐ถ๐ด๐๐ฎ๐๐ถ๐ผ๐ป, ๐ฎ๐ป๐ฑ ๐น๐ถ๐ป๐ธ๐ถ๐ป๐ด ๐
It resolves what references actually point to, then links entities, citations, and cross-references into a single coherent graph.
โข ๐๐ฟ๐ฎ๐ฝ๐ต-๐ณ๐ถ๐ฟ๐๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ฐ๐ ๐โโก๏ธ
Small enough to run locally on a consumer PC with sub-second latency, and it stays reliable on long documents where front
To read more about our new model, check out our latest Hugging Face article:
https://huggingface.co/blog/isaacus/introducing-kanon-2-enricher
Today weโre publicly releasing Kanon 2 Enricher, and with it, an entirely new class of AI model that weโre calling a hierarchical graphitization model.
This is fundamentally different from both universal extraction models and generative models.
As a hierarchical graphitization model, Kanon 2 Enricher natively outputs a ๐ธ๐ป๐ผ๐๐น๐ฒ๐ฑ๐ด๐ฒ ๐ด๐ฟ๐ฎ๐ฝ๐ต rather than tokens, which makes it architecturally incapable of hallucinating or inventing text that wasnโt present in the input.
What that enables in practice is unlike any other model or ML architecture on the market:
โข ๐ก๐ผ ๐ต๐ฎ๐น๐น๐๐ฐ๐ถ๐ป๐ฎ๐๐ถ๐ผ๐ป๐ ๐ค
It cannot hallucinate. All references and links are stored as spans, meaning exact character offsets anchored to the original text.
โข ๐๐ถ๐ฒ๐ฟ๐ฎ๐ฟ๐ฐ๐ต๐ถ๐ฐ๐ฎ๐น ๐๐ฒ๐ด๐บ๐ฒ๐ป๐๐ฎ๐๐ถ๐ผ๐ป, ๐ป๐ผ๐ ๐ท๐๐๐ ๐ฒ๐ ๐๐ฟ๐ฎ๐ฐ๐๐ถ๐ผ๐ป ๐
It deconstructs a documentโs full nested hierarchy, down to chapters, sections, clauses, schedules, signatures, and even singular sentences, and classifies each span with dozens of contextual features.
โข ๐๐ป๐๐ถ๐๐ ๐ฒ๐ ๐๐ฟ๐ฎ๐ฐ๐๐ถ๐ผ๐ป, ๐ฑ๐ถ๐๐ฎ๐บ๐ฏ๐ถ๐ด๐๐ฎ๐๐ถ๐ผ๐ป, ๐ฎ๐ป๐ฑ ๐น๐ถ๐ป๐ธ๐ถ๐ป๐ด ๐
It resolves what references actually point to, then links entities, citations, and cross-references into a single coherent graph.
โข ๐๐ฟ๐ฎ๐ฝ๐ต-๐ณ๐ถ๐ฟ๐๐ ๐ฒ๐ณ๐ณ๐ถ๐ฐ๐ถ๐ฒ๐ป๐ฐ๐ ๐โโก๏ธ
Small enough to run locally on a consumer PC with sub-second latency, and it stays reliable on long documents where front
To read more about our new model, check out our latest Hugging Face article:
https://huggingface.co/blog/isaacus/introducing-kanon-2-enricher
abdurrahmanbutlerย
published an
article 13 days ago
Article
Introducing Kanon 2 Enricher โ the worldโs first hierarchical graphitization model
โข
6
umarbutlerย
authored a paper 13 days ago
abdurrahmanbutlerย
authored a paper 13 days ago
umarbutlerย
updated a collection 13 days ago
umarbutlerย
submitted a paper to Daily Papers 13 days ago
abdurrahmanbutlerย
updated a dataset 20 days ago
umarbutlerย
updated a collection 22 days ago