T. Liu, S. Zhang and Q. Xiong, "Separated Model for Stopping Point Prediction of Autoregressive Sequence," 2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS), Xiangtan, China, 2023, pp. 799-803, doi: 10.1109/DDCLS58216.2023.10167110.
T. Liu, S. Zhang and Q. Xiong, "Separated Model for Stopping Point Prediction of Autoregressive Sequence," 2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS), Xiangtan, China, 2023, pp. 799-803, doi: 10.1109/DDCLS58216.2023.10167110.
T. Liu, S. Zhang and Q. Xiong, "Separated Model for Stopping Point Prediction of Autoregressive Sequence," 2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS), Xiangtan, China, 2023, pp. 799-803, doi: 10.1109/DDCLS58216.2023.10167110.
T. Liu, S. Zhang and Q. Xiong, "Separated Model for Stopping Point Prediction of Autoregressive Sequence," 2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS), Xiangtan, China, 2023, pp. 799-803, doi: 10.1109/DDCLS58216.2023.10167110.
Abstract
While the language model using the stop sign as an independent token has been widely used to decide when the model should stop, it may lead to the growth of vocabulary dimensions and further problems. Similarly, present research on game algorithms usually estimate stopping point related problems based on the evaluation of the winning rate. However, information redundancy may also exist in such models, thus increasing the training difficulty. Above two types of tasks (and similar autoregressive tasks) show a common problem of stopping point prediction. In this paper, we describe a design of separated model, trying to separate the complexity of stopping point prediction from the main task model, so that the information used for estimating stopping point can be reduced. On this basis, in order to verify the rationality of using separated model, we propose a model-free test method. It judges the separability of transformed data based on point difference and sequence difference metrics. In this way, it can predict the credibility of the separated model inference.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.