1 citations · 4 across the 9 of their papers we have counts for
9 papers
Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling
Jannek Ulm, Kevin Du, Vésteinn Snæbjarnarson
Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to…
How Persuasive is Your Context?
Tu Nguyen, Kevin Du, Alexander Miserlis Hoyle +1
Two central capabilities of language models (LMs) are: (i) drawing on prior knowledge about entities, which allows them to answer queries such as "What's the official language of A…
Taxonomy-Aware Evaluation of Vision-Language Models
Vésteinn Snæbjarnarson, Kevin Du, Niklas Stoehr +4
When a vision-language model (VLM) is prompted to identify an entity depicted in an image, it may answer 'I see a conifer,' rather than the specific label 'norway spruce'. This rai…
Controllable Context Sensitivity and the Knob Behind It
Julian Minder, Kevin Du, Niklas Stoehr +4
When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamen…
Efficiently Computing Susceptibility to Context in Language Models
Tianyu Liu, Kevin Du, Mrinmaya Sachan +1
One strength of modern language models is their ability to incorporate information from a user-input context when answering queries. However, they are not equally sensitive to the…
Activation Scaling for Steering and Interpreting Language Models
Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson +3
Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant act…
Context versus Prior Knowledge in Language Models
Kevin Du, Vésteinn Snæbjarnarson, Niklas Stoehr +3
To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perfor…
The Causal Influence of Grammatical Gender on Distributional Semantics
Karolina Stańczak, Kevin Du, Adina Williams +2
How much meaning influences gender assignment across languages is an active area of research in linguistics and cognitive science. We can view current approaches as aiming to deter…
Generalizing Backpropagation for Gradient-Based Interpretability
Kevin Du, Lucas Torroba Hennigen, Niklas Stoehr +2
Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs. While these methods c…