1 citations · 1 across the 3 of their papers we have counts for
7 papers
Which Attention Heads are like the Human Head? Not the Ones that Compute
Christopher Pinier, Gustaw Opiełka, Hannes Rosenbusch +3
Brain-AI alignment is often interpreted as a sign that model and brain perform similar computations. Whether the aligned units are causally involved in model computation is rarely…
Causality Invariance: Function and Concept Vectors in LLMs
Gustaw Opiełka, Hannes Rosenbusch, Claire E. Stevenson
Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning…
Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
Gustaw Opiełka, Hannes Rosenbusch, Claire E. Stevenson
Analogical reasoning relies on conceptual abstractions, but it is unclear whether Large Language Models (LLMs) harbor such internal representations. We explore distilled representa…
Which books do I like?
Hannes Rosenbusch, Erdem Ozan Meral
Finding enjoyable fiction books can be challenging, partly because stories are multi-faceted and one's own literary taste might be difficult to ascertain. Here, we introduce the IS…
Are some books better than others?
Hannes Rosenbusch, Luke Korthals
Scholars, awards committees, and laypeople frequently discuss the merit of written works. Literary professionals and journalists differ in how much perspectivism they concede in th…
Do Large Language Models Solve ARC Visual Analogies Like People Do?
Gustaw Opiełka, Hannes Rosenbusch, Veerle Vijverberg +1
The Abstraction Reasoning Corpus (ARC) is a visual analogical reasoning test designed for humans and machines (Chollet, 2019). We compared human and large language model (LLM) perf…
Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method
Luca H. Thoms, Karel A. Veldkamp, Hannes Rosenbusch +1
Analogical reasoning derives information from known relations and generalizes this information to similar yet unfamiliar situations. One of the first generalized ways in which deep…