7 papers
Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures
Supantho Rakshit, Adele Goldberg, Henry Conklin
As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains.…
Learning is Forgetting: LLM Training As Lossy Compression
Henry C. Conklin, Tom Hosking, Tan Yi-Chern +5
Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our abilit…
Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models
Qiawen Ella Liu, Marina Dubova, Henry Conklin +2
Creative ideas often arise by associating remote concepts. Can random associations reliably increase originality, and do they help humans and large language models (LLMs) in the sa…
Information Structure in Mappings: An Approach to Learning, Representation, and Generalisation
Henry Conklin
Despite the remarkable success of large large-scale neural networks, we still lack unified notation for thinking about and describing their representational spaces. We lack methods…
Representations as Language: An Information-Theoretic Framework for Interpretability
Henry Conklin, Kenny Smith
Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of t…
Anaphoric Structure Emerges Between Neural Networks
Nicholas Edwards, Hannah Rohde, Henry Conklin
Pragmatics is core to natural language, enabling speakers to communicate efficiently with structures like ellipsis and anaphora that can shorten utterances without loss of meaning.…
Meta-Learning to Compositionally Generalize
Henry Conklin, Bailin Wang, Kenny Smith +1
Natural language is compositional; the meaning of a sentence is a function of the meaning of its parts. This property allows humans to create and interpret novel sentences, general…