6 papers
When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
Hope McGovern, Caroline Craig, Thomas Lippincott +1
Analogical reasoning is a core cognitive faculty essential for narrative understanding. While LLMs perform well when surface and structural cues align, they struggle in cases where…
Pretraining Language Models for Diachronic Linguistic Change Discovery
Elisabeth Fittschen, Sabrina Li, Tom Lippincott +2
Large language models (LLMs) have shown potential as tools for scientific discovery. This has engendered growing interest in their use in humanistic disciplines, such as historical…
Dynamic Embedded Topic Models: properties and recommendations based on diverse corpora
Elisabeth Fittschen, Bella Xia, Leib Celnik +2
We measure the effects of several implementation choices for the Dynamic Embedded Topic Model, as applied to five distinct diachronic corpora, with the goal of isolating important…
Transferring Extreme Subword Style Using Ngram Model-Based Logit Scaling
Craig Messner, Tom Lippincott
We present an ngram model-based logit scaling technique that effectively transfers extreme subword stylistic variation to large language models at inference time. We demonstrate it…
Computational Discovery of Chiasmus in Ancient Religious Text
Hope McGovern, Hale Sirin, Tom Lippincott
Chiasmus, a debated literary device in Biblical texts, has captivated mystics while sparking ongoing scholarly discussion. In this paper, we introduce the first computational appro…
Characterizing the Effects of Translation on Intertextuality using Multilingual Embedding Spaces
Hope McGovern, Hale Sirin, Tom Lippincott
Rhetorical devices are difficult to translate, but they are crucial to the translation of literary documents. We investigate the use of multilingual embedding spaces to characteriz…