Search Results for author:
Found 4 papers, 0 papers with code
Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall
By further decoupling model known and unknown knowledge, we find the degradation is attributed to exemplars that contradict a model's known knowledge, as well as the number of such exemplars.
CoSiNES: Contrastive Siamese Network for Entity Standardization
Entity standardization maps noisy mentions from free-form text to standard entities in a knowledge base.
Conversation Modeling to Predict Derailment
We propose a domain-adaptive pretraining objective to integrate conversational structure information and a multitask learning scheme to leverage the distance from each utterance to derailment.
Extracting Incidents, Effects, and Requested Advice from MeToo Posts
We develop a natural language-based model to identify sentences from a post that describe any of the above three categories.
