Who owns the model? Where should a legal team's intelligence live? These questions are at the center of many conversations in legal AI, but we think the most important question to answer is: what produces the best outcome for every legal task? As CTO @jacsebl and CPO Bryan Tsao explain, there is no best model. Different models lead on different tasks, and the frontier changes almost weekly. At Legora, we use the best available model for each task, and invest in the system, where intelligence compounds and remains editable, auditable, and portable. We post-train when we know it delivers our customers better performance on a specialized task. Training is a tool, not a strategy. No lawyer should have to worry about which model did the work. Just whether the work holds up.

There is no best model. There's a lot of noise about models right now. Who is training them, who owns them, where legal intelligence should live. One question actually matters: what produces the best outcome for the legal task in front of you? That's how we decide things at @WeareLegora. We optimize for the end-to-end outcome on a legal task. The model is one layer of that system, not the system. Models are uneven and the frontier changes almost weekly. One model plans a long job well, another runs deep analysis across thousands of documents. Some have to be told exactly what to do, and some are fine with a vague brief. They all break in different ways. So our lawyers write evals and we test them with the Legora BAR, our benchmark for agentic reasoning. Every model takes every test, and the model that wins gets the work. We post-train when we know it buys our customers better performance on a specialized task. Training is a tool we reach for when it helps, nothing more than that. The intelligence that compounds sits in the orchestration layer. Precedents, review standards, client requirements. That knowledge has to stay editable, auditable and portable. In our system, a changed review standard is an edit that takes effect the same day, with no new model training required. No lawyer should have to worry about which model did the work, any more than they think about which chip is in their laptop. They should only care about the quality of the work. That's what we are focused on. If you want the engineering version of this argument rather than the CEO version, our CPO, Bryan Tsao, and CTO, @jacsebl, take it apart in the video below.

One open question for anyone finetuning models is - how "post-trainable" are different open source models? We can theorize that models that reside in shallower loss curves are more amenable to post-training - which makes sense, given that it requires less gradient updates to modify behavior. Then, this paper proposes a pre-training algorithm that makes a model more post-trainable. The idea is straightforward once you wrap you head around it: 1. Find the worst policy locally around the policy pi (found by taking the inverse gradient w.r.t pi), call that pi_prime 2. Take the gradient at pi_prime (call that grad[pi_prime] ) 3. Apply grad[pi_prime] to pi. The intuition is that we're actually moving in the direction that benefits the worst model around you, meaning a model maintains post-trainability because we maintain a shallow loss landscape. Another way to imagine this, is it effectively avoids steep pot-holes during pretraining that would lock your model in a distribution that it can't post-train its way out of. Really great work from @IshaanWatts18, @CatherineL11638, @goyalsachin007, @jacspringer, @AdtRaghunathan. It's our favorite paper of the month at Trajectory!