16 citations · 73 across the 18 of their papers we have counts for
7 papers · 1 filter
LLM Unlearning Without an Expert Curated Dataset
Xiaoyuan Zhu, Muru Zhang, Ollie Liu +2
Modern large language models often encode sensitive, harmful, or copyrighted knowledge, raising the need for post-hoc unlearning-the ability to remove specific domains of knowledge…
Resa: Transparent Reasoning Models via SAEs
Shangshang Wang, Julian Asilis, Ömer Faruk Akgül +4
How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning…
Tina: Tiny Reasoning Models via LoRA
Shangshang Wang, Julian Asilis, Ömer Faruk Akgül +3
How cost-effectively can strong reasoning abilities be achieved in language models? Driven by this fundamental question, we present Tina, a family of tiny reasoning models achieved…
MatViX: Multimodal Information Extraction from Visually Rich Articles
Ghazal Khalighinejad, Sharon Scott, Ollie Liu +4
Multimodal information extraction (MIE) is crucial for scientific literature, where valuable data is often spread across text, figures, and tables. In materials science, extracting…
On Retrieval Augmentation and the Limitations of Language Model Training
Ting-Rui Chiang, Xinyan Velocity Yu, Joshua Robinson +3
Augmenting a language model (LM) with -nearest neighbors (NN) retrieval on its training data alone can decrease its perplexity, though the underlying reasons for this remain…
Approximating CKY with Transformers
Ghazal Khalighinejad, Ollie Liu, Sam Wiseman
We investigate the ability of transformer models to approximate the CKY algorithm, using them to directly predict a sentence's parse and thus avoid the CKY algorithm's cubic depend…
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
Michael Hanna, Ollie Liu, Alexandre Variengien
Pre-trained language models can be surprisingly adept at tasks they were not explicitly trained on, but how they implement these capabilities is poorly understood. In this paper, w…