5 papers
TaxoSAE: Rethinking Sparse Autoencoders through Taxonomic Logic
Xinyu Guo, Minglai Yang, Clayton T. Morrison +2
Recent Sparse Autoencoders (SAEs) decompose the representations of large language models (LLMs) into interpretable features, enabling precise readout and control of encoded knowled…
Bidirectional Small-Granularity Search between Code and Text
Marco A. Valenzuela-Escárcega, Enrique Noriega-Atala, Gus Hahn-Powell +2
We introduce the novel task of bidirectional small-granularity search between code and text, where the queries are small snippets of text or code and the results are also small fra…
Variable Extraction for Model Recovery in Scientific Literature
Chunwei Liu, Enrique Noriega-Atala, Adarsh Pyarelal +2
The global output of academic publications exceeds 5 million articles per year, making it difficult for humans to keep up with even a tiny fraction of scientific output. We need me…
When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context
Enrique Noriega-Atala, Robert Vacareanu, Salena Torres Ashton +3
We introduce a neural architecture finetuned for the task of scenario context generation: The relevant location and time of an event or entity mentioned in text. Contextualizing in…
An Overview + Detail Layout for Visualizing Compound Graphs
Chang Han, Justin Lieffers, Clayton Morrison +1
Compound graphs are networks in which vertices can be grouped into larger subsets, with these subsets capable of further grouping, resulting in a nesting that can be many levels de…