Papers by Anthony Hunter

3 papers
Identifying Linear Relational Concepts in Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: a technique for finding concept directions for human-interpretable concepts is needed to find their direction in the latent space . a linear relational concept (LRC) can be used to locate concepts in hidden activations .
Approach: They propose a method for finding human-interpretable concepts by inverting a linear relational embedding and using earlier object layers.
Outcome: The proposed method outperforms standard probing classifiers on performance as concept classifier and ability to causally change model output.
PizzaCommonSense: A Dataset for Commonsense Reasoning about Intermediate Steps in Cooking Recipes (2024.findings-emnlp)

Copied to clipboard

Challenge: Understanding procedural texts is essential for enabling machines to follow instructions and reason about tasks.
Approach: They propose a corpus of cooking recipes enriched with descriptions of intermediate steps . they propose enabling machines to follow instructions and reason about tasks .
Outcome: The proposed model achieves only 26% human-evaluated preference for generations . pizzaCommonsense is a benchmark for the reasoning capabilities of large language models .
Understanding the Cooking Process with English Recipe Text (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to translate recipes into a flow graph have performance problems . authors propose a framework to construct a graph from recipe text .
Approach: They propose a framework that can be used to translate recipes into a flow graph representation.
Outcome: The proposed framework can predict the edge label and achieve the overall F1 score of 92.2 on the English recipe flow graph corpus.

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