Papers by Xibin Gao
Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be prohibitive in terms of feasibility, time, and resources. |
| Approach: | They propose a method for training large language models by enabling "self-talk" they propose supervised fine-tuning of LLMs to improve quality of dialogues . |
| Outcome: | The proposed method generates training data via "self-talk" of LLMs that can be refined and utilized for supervised fine-tuning. |
Backward Compatibility During Data Updates by Weight Interpolation (2024.eacl-long)
Copied to clipboard
| Challenge: | Retraining a model with a larger amount of training data introduces negative flips . retraining the model with the updated data introduce negative flipping . |
| Approach: | They propose a backward compatible weight interpolation method to improve model predictions without regression bugs. |
| Outcome: | The proposed method reduces negative flips without sacrificing accuracy . it is straight forward to implement and does not increase inference cost. |