139 citations · 256 across the 34 of their papers we have counts for
6 papers · 1 filter
Reconstruction Probing
Najoung Kim, Jatin Khilnani, Alex Warstadt +1
We propose reconstruction probing, a new analysis method for contextualized representations based on reconstruction probabilities in masked language models (MLMs). This method reli…
Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models
Najoung Kim, Tal Linzen, Paul Smolensky
Human linguistic capacity is often characterized by compositionality and the generalization it enables -- human learners can produce and comprehend novel complex expressions by com…
LAMBADA: Backward Chaining for Automated Reasoning in Natural Language
Mehran Kazemi, Najoung Kim, Deepti Bhatia +2
Remarkable progress has been made on automated reasoning with natural text, by using Language Models (LMs) and methods such as Chain-of-Thought and Selection-Inference. These techn…
(QA): Question Answering with Questionable Assumptions
Najoung Kim, Phu Mon Htut, Samuel R. Bowman +1
Naturally occurring information-seeking questions often contain questionable assumptions -- assumptions that are false or unverifiable. Questions containing questionable assumption…
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
BigScience Workshop, :, Teven Le Scao +391
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to wi…
Inverse scaling can become U-shaped
Jason Wei, Najoung Kim, Yi Tay +1
Scaling up language models has been empirically shown to improve performance on a wide range of downstream tasks. However, if we were to observe worse performance as a function of…