Papers with RIPA

2 papers
Understanding Undesirable Word Embedding Associations (P19-1)

Copied to clipboard

Challenge: Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes.
Approach: They propose to use subspace projection to debias vectors post hoc using a model that implicitly does matrix factorization to debunk gender bias.
Outcome: The proposed test overestimates gender bias in word embeddings by using subspace projection, a method that is widely used in training.
KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies indicate that language models generate non-factual information that is not supported by evidence with a high level of confidence.
Approach: They propose a knowledge-constrained decoding method that guides a frozen LLM to generate text aligned with the reference knowledge at each decoding step.
Outcome: The proposed method reduces the risk of misinformation generated by LLMs by reducing training costs and catastrophic forgetting for multi-tasking models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations