Systems and methods for interface-based machine learning model output customization
Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.
1. A system for interface-based evaluation output customization, the system comprising:
a memory comprising:
a content library database containing a plurality of prompts and evaluation data associated with each of the plurality of prompts; and
a model database comprising a plurality of evaluation models for automated evaluation of received user responses, wherein the evaluation data of each of the plurality of prompts comprises a pointer linking to the associated evaluation model; and
at least one processor configured to:
receive a plurality of responses from a plurality of users to a provided prompt from the plurality of prompts;
evaluate the received plurality of responses with an evaluation model from the plurality of evaluation models, the evaluation model comprising a machine learning model trained to output a score relevant to at least portions of a response;
generate evaluation data characterizing at least one attribute of the evaluated plurality of responses;
generate an output panel comprising at least one performance modification interface, wherein the at least one performance modification interface identifies an attribute of the evaluated plurality of responses, and wherein the at least one performance modification interface comprises an input feature, wherein the input feature is user manipulable to directly change the attribute of the evaluated plurality of responses after receipt of the plurality of responses;
receive an input via the input feature;
modify the attribute of the evaluated plurality of responses; and
generate updated evaluation data based at least in part on the modified attribute of the evaluated plurality of responses.
2. The system of claim 1 , wherein the attribute of the evaluated plurality of responses comprises a score distribution generated by the evaluation model.
3. The system of claim 2 , wherein the input received via the input feature changes at least one of: a shape of the score distribution and a width of the score distribution.
4. The system of claim 2 , wherein evaluating the received responses comprises generating a first score for each of the received response; and wherein generating updated evaluation data comprises generating a second score for each of the received responses, wherein the second score is generated at least in part based on the input received via the input feature.
5. The system of claim 4 , wherein the output panel further comprises a model panel characterizing at least one attribute of the evaluation model.
6. The system of claim 5 , wherein the at least one attribute of the evaluation model comprises at least one of: a generic evaluation parameter; and a model identifier.
7. The system of claim 6 , wherein the generic evaluation parameter identifies an application stringency.
8. The system of claim 7 , wherein the generic evaluation parameter comprises at least one of: a formatting style; a proficiency level; and a language.
9. The system of claim 7 , wherein the output panel comprises selection feature whereby a user can select one of a plurality of generic evaluation parameters, and wherein the evaluation model training is based at least in part of each of the plurality of generic evaluation parameters.
10. A method for interface-based evaluation output customization, the method comprising:
receiving a plurality of responses from a plurality of users to a provided prompt from a plurality of prompts included in a content library database;
evaluating the received plurality of responses with an evaluation model from a plurality of evaluation models included in a model database, the evaluation model comprising a machine learning model trained to output a score relevant to at least portions of a response;
generating evaluation data characterizing at least one attribute of the evaluated plurality of responses;
generating an output panel comprising at least one performance modification interface, wherein the at least one performance modification interface identifies an attribute of the evaluated plurality of responses, and wherein the at least one performance modification interface comprises an input feature, wherein the input feature is user manipulable to directly change the attribute of the evaluated plurality of responses after receipt of the plurality of responses;
receiving an input via the input feature;
modifying the attribute of the evaluated plurality of responses; and
generating updated evaluation data based at least in part on the modified attribute of the evaluated plurality of responses.
11. The method of claim 10 , wherein the attribute of the evaluated plurality of responses comprises a score distribution generated by the evaluation model.
12. The method of claim 11 , wherein the input received via the input feature changes at least one of: a shape of the score distribution; a width of the score distribution; and a center of the score distribution.
13. The method of claim 11 , wherein evaluating the received responses comprises generating a first score for each of the received response; and wherein generating updated evaluation data comprises generating a second score for each of the received responses, wherein the second score is generated at least in part based on the input received via the input feature.
14. The method of claim 13 , wherein the output panel further comprises a model panel characterizing at least one attribute of the evaluation model.
15. The method of claim 14 , wherein the at least one attribute of the evaluation model comprises at least one of: a generic evaluation parameter; and a model identifier.
16. The method of claim 15 , wherein the generic evaluation parameter identifies: a selected generic evaluation parameter; and an application stringency.
17. The method of claim 16 , wherein the generic evaluation parameter comprises at least one of: a formatting style; a proficiency level; and a language.
18. The method of claim 16 , wherein the output panel comprises selection feature whereby a user can select one of a plurality of generic evaluation parameters, and wherein the evaluation model training is based at least in part of each of the plurality of generic evaluation parameters.