Because LLMs often confuse my input and their own output I have long wondered whether it might be a good idea to put the tag-processing into the harness and use specific experts (in a MoE) or LoRAs for the tokens in each tag.
That way one can train against instruction following within tool-tags without hurting instruction following generally etc.
Your work makes that sound like an even better idea.
Because LLMs often confuse my input and their own output I have long wondered whether it might be a good idea to put the tag-processing into the harness and use specific experts (in a MoE) or LoRAs for the tokens in each tag.
That way one can train against instruction following within tool-tags without hurting instruction following generally etc.
Your work makes that sound like an even better idea.