Papers by Shubhendu Trivedi
Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Currently, the most commonly used confidence score is the likelihood of the generated sequence . different tokens should be weighted differently depending on the context. |
| Approach: | They propose to assign different weights to various tokens using attention values elicited from the base LLM. |
| Outcome: | The proposed model improves the confidence of the predicted sequence probability by assigning weights to tokens based on attention values elicited from the base model. |