# LAMMR · DTSC

> Choose the model suited to each legal task, with traceable decisions.

Source: https://www.dtsc.be/en/brain/projects/lammr/

DTSC

BRAIN / Applied research

# LAMMR

Choose the model suited to each legal task, with traceable decisions.

BRAIN

LAMMR

Legal AI · Model routing

BRAIN

No. 08

08

LAMMR

BRAIN

Past research · HHAI 2026

LLM

Assessment

Traceability

Past research · HHAI 2026

Legal AI · Model routing

### Project status

Past research · HHAI 2026

HHAI 2026 · Brussels, July 2026

- LLM

- Assessment

- Traceability

### Partners

- CONTRACTO - research collaboration

Project code

## The approach

LAMMR stands for Legal Adaptive Multi-Model Router. Extracting clauses and interpreting legal obligations require different capabilities: the system routes each task to the most suitable language model.

Routing combines rules and a learned predictor. Each decision is logged to enable audit. The evaluation distinguishes extraction from reasoning, so that a good result in one domain does not mask errors in the other.

The system was validated on over 1,000 legal tasks and shows significant improvements over the deployment of a single model.

Led by Aditya Mukhopadhyay and arising from a collaboration with the startup CONTRACTO, LAMMR was accepted at HHAI 2026 and presented in Brussels in July. This fact sheet gathers the work previously presented under the title “AI for Corporate”.

Project architecture · Open the diagram to enlarge

## The contributions

Aditya Mukhopadhyay

BRAIN Member

Source: BRAIN portfolio.

Discuss this project
