73 citations · 74 across the 3 of their papers we have counts for
3 papers
cs.CL2023★ 73 cited
How Language Model Hallucinations Can Snowball
Muru Zhang, Ofir Press, William Merrill +2
A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs,…
cs.LG2023
A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks
William Merrill, Nikolaos Tsilivis, Aman Shukla
Grokking is a phenomenon where a model trained on an algorithmic task first overfits but, then, after a large amount of additional training, undergoes a phase transition to general…
cs.LG2022★ 1 cited
Extracting Finite Automata from RNNs Using State Merging
William Merrill, Nikolaos Tsilivis
One way to interpret the behavior of a blackbox recurrent neural network (RNN) is to extract from it a more interpretable discrete computational model, like a finite state machine,…