RouteLLM: Learning to Route LLMs with Preference Data — mentioned by gardnr

Mon, 23 Dec 2024 06:51:53 GMT

In case you haven't seen this one yet: Title: "RouteLLM: Learning to Route LLMs with Preference Data" Abstract: Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with higher expenses, while less capable models are more cost-effective. To address this dilemma, we propose several efficient router models that dynamically select between a stronger and a weaker LLM during inference, aiming to optimize the balance between…

Paper and discussion history. A mention is not an endorsement.

RouteLLM: Learning to Route LLMs with Preference Data · HackerPapers discussions

RouteLLM: Learning to Route LLMs with Preference Data — mentioned by gardnr