Papers by Yoav Levine

4 papers
Generating Benchmarks for Factuality Evaluation of Language Models (2024.eacl-long)

Copied to clipboard

Challenge: Existing methods for factuality evaluation of LLM generation focus on facts sampled from the LM itself and might under-represent domain specific or rare facts.
Approach: They propose a method that transforms a factual corpus into a benchmark evaluating an LM's propensity to generate true facts from the corpus .
Outcome: The proposed framework transforms a factual corpus of interest into a benchmark evaluating an LM's propensity to generate true facts from the corpus vs. similar but incorrect statements.
SenseBERT: Driving Some Sense into BERT (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches for self-supervision operate at word form level, which serves as a surrogate for the underlying semantic content.
Approach: They propose a method to employ weak-supervision directly at the word sense level, without the use of human annotation.
Outcome: The proposed model achieves significantly improved lexical understanding without human annotation on the ‘Word in Context’ task.
In-Context Retrieval-Augmented Language Models (2023.tacl-1)

Copied to clipboard

Challenge: Existing RALM methods focus on modifying the LM architecture to facilitate incorporation of external information, complicating deployment.
Approach: They propose to condition a language model on relevant documents from a grounding corpus during generation by conditioning on external knowledge sources.
Outcome: The proposed method significantly improves language modeling performance and provides natural source attribution mechanism.
Parallel Context Windows for Large Language Models (2023.acl-long)

Copied to clipboard

Challenge: Existing efforts to address context window limitation for off-the-shelf LLMs involve training specialized architectures.
Approach: They propose a method that carves a long context into chunks and restricts attention to apply only within each window.
Outcome: The proposed method shows significant improvements on in-context learning tasks with diverse input and output spaces.

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