Papers by Anthony Hunter
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. |